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

    Neuronpedia

    INDEX
    Explanations

    references to emotional responses and personal concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.38
     auto
    -0.32
     to
    -0.30
    ings
    -0.29
     od
    -0.29
     Cowan
    -0.29
     screen
    -0.28
    '
    -0.28
     via
    -0.28
    auto
    -0.28
    POSITIVE LOGITS
     considerably
    0.99
     greatly
    0.97
     significantly
    0.96
     immensely
    0.89
    slightly
    0.88
     slightly
    0.87
     appreciably
    0.84
     massively
    0.83
     tremendously
    0.82
     substantially
    0.82
    Act Density 0.381%

    No Known Activations