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

    Neuronpedia

    INDEX
    Explanations

    references to self-identity and personal ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoresizingMask
    -0.61
     ſhall
    -0.58
    rilled
    -0.56
    cino
    -0.56
    umą
    -0.55
    move
    -0.54
    )_/¯
    -0.54
    oté
    -0.53
     vectorielles
    -0.53
    SharedCtor
    -0.52
    POSITIVE LOGITS
     sendiri
    0.75
     jij
    0.67
    Hvem
    0.65
     Myself
    0.64
    herself
    0.63
     herself
    0.62
     Who
    0.59
     own
    0.58
     *>(
    0.58
     Yourself
    0.58
    Act Density 0.187%

    No Known Activations