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

    Neuronpedia

    INDEX
    Explanations

    words related to jokes and humor

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to specific situations or circumstances involving events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angan
    -0.94
     Aging
    -0.78
    izoph
    -0.68
    atown
    -0.67
    ibaba
    -0.64
    DATA
    -0.64
    fw
    -0.63
    Ô
    -0.62
    gall
    -0.60
     Neuroscience
    -0.60
    POSITIVE LOGITS
     extraord
    1.09
     who
    1.02
    esses
    0.99
    Joined
    0.98
     whom
    0.95
    friend
    0.87
    ess
    0.81
    who
    0.79
    stration
    0.78
    ials
    0.77
    Act Density 0.350%

    No Known Activations