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

    Neuronpedia

    INDEX
    Explanations

    adverbs that express certainty or emphasize a point

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate certainty or frequency of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mour
    -0.81
    soDeliveryDate
    -0.69
    ylum
    -0.69
     Standing
    -0.63
    reth
    -0.63
    ULTS
    -0.63
    76561
    -0.61
    forced
    -0.61
     Essential
    -0.60
    Mesh
    -0.60
    POSITIVE LOGITS
     afford
    1.36
     rely
    0.93
     imagine
    0.91
     argue
    0.89
     manipulate
    0.89
     muster
    0.86
     relate
    0.84
     accuse
    0.83
     claim
    0.82
     boast
    0.81
    Act Density 0.077%

    No Known Activations