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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members, especially fathers

    oai_token-act-pair · gpt-3.5-turbo

    statements about family and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.86
    etheless
    -0.72
    ãĢĤ
    -0.71
    .*
    -0.69
    .).
    -0.67
    %.
    -0.67
     ).
    -0.61
    ?).
    -0.61
    .</
    -0.60
    ttp
    -0.59
    POSITIVE LOGITS
    ,"
    1.38
    ,'"
    1.28
    ),"
    1.22
     [
    1.16
    ,''
    1.13
    %"
    1.03
    .,"
    1.02
    ',"
    0.98
    "—
    0.94
    ,'
    0.93
    Act Density 1.079%

    No Known Activations