© 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. 3070
    Prev
    Next
    INDEX
    Explanations

    instances of the word "campaign."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Thom
    -0.77
     weddings
    -0.74
     TAMADRA
    -0.67
    龍
    -0.67
     Bride
    -0.63
     Oscars
    -0.62
     Nebula
    -0.61
    REAM
    -0.60
    の魔
    -0.58
    iculture
    -0.58
    POSITIVE LOGITS
    puff
    0.79
    lua
    0.77
    tyard
    0.70
    wagen
    0.68
     dashed
    0.67
    imity
    0.67
    dding
    0.67
    ti
    0.66
    psc
    0.66
     hatched
    0.65
    Activations Density 0.036%

    No Known Activations