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

    Neuronpedia

    INDEX
    Explanations

    mentions of the scale or extent of various situations or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate magnitude or scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erenn
    -0.78
    cellaneous
    -0.77
    ade
    -0.75
    waukee
    -0.74
    nob
    -0.74
    center
    -0.72
    pretty
    -0.72
    advertising
    -0.71
    nis
    -0.69
     âĨij
    -0.69
    POSITIVE LOGITS
     their
    0.80
     difference
    0.80
     disparity
    0.78
     commitment
    0.77
     bribes
    0.77
     penalties
    0.76
     hostilities
    0.76
     commitments
    0.75
     these
    0.75
     penetration
    0.75
    Act Density 0.146%

    No Known Activations