© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3140
    Prev
    Next
    INDEX
    Explanations

    instances of the word "trying" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    raped
    -0.89
    arc
    -0.82
    ESE
    -0.79
    among
    -0.77
    orders
    -0.77
    ikh
    -0.76
    enger
    -0.74
    inson
    -0.72
    apes
    -0.72
    ources
    -0.71
    POSITIVE LOGITS
     valiant
    0.78
    uyomi
    0.64
     hard
    0.64
     superf
    0.63
    �醒
    0.62
     Shinra
    0.60
     to
    0.60
     sqor
    0.60
    ��
    0.59
     desperately
    0.59
    Activations Density 0.034%

    No Known Activations