© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 716
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring 'ich'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.68
     Disciple
    -0.66
     surname
    -0.62
     precinct
    -0.60
     symp
    -0.59
    conom
    -0.58
     disapp
    -0.57
     strictly
    -0.56
     cour
    -0.56
     inheritance
    -0.56
    POSITIVE LOGITS
    bender
    0.77
    arted
    0.77
    anamo
    0.70
    vr
    0.66
    rals
    0.66
    Sad
    0.65
    ��
    0.64
    inka
    0.61
    atives
    0.61
    Untitled
    0.61
    Activations Density 0.012%

    No Known Activations