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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and phrases indicating ownership or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Heads
    -0.69
    Lives
    -0.66
    DockStyle
    -0.66
     careers
    -0.63
     bodies
    -0.63
     personalities
    -0.61
     Heads
    -0.61
    heads
    -0.61
     Lives
    -0.60
    lives
    -0.59
    POSITIVE LOGITS
     face
    0.73
    RenderAtEndOf
    0.66
    0.60
    StoreMessageInfo
    0.57
     eye
    0.55
    MigrationBuilder
    0.55
     collective
    0.55
     craw
    0.54
     dankbar
    0.53
    ]-->
    0.52
    Act Density 0.228%

    No Known Activations