Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "head" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to heads or head-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autos
    -0.69
     Niet
    -0.68
     Mub
    -0.65
    eers
    -0.65
     Parenthood
    -0.63
    PsyNetMessage
    -0.62
    ISM
    -0.62
     CK
    -0.61
     recip
    -0.60
     Grande
    -0.59
    POSITIVE LOGITS
    butt
    1.35
    canon
    1.34
    gear
    1.31
    dress
    1.28
    scar
    1.24
    quarter
    1.23
    quarters
    1.20
    liners
    1.19
    liner
    1.16
    shots
    1.14
    Act Density 0.043%

    No Known Activations