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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing a decision or an action being taken

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate action or decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortment
    -0.74
    soDeliveryDate
    -0.67
    itton
    -0.66
    yssey
    -0.64
     largeDownload
    -0.62
     undoubtedly
    -0.61
    unknown
    -0.60
     doubtless
    -0.59
     awaited
    -0.58
     hopefully
    -0.58
    POSITIVE LOGITS
     anymore
    1.71
     nor
    1.40
     anything
    1.26
     any
    1.23
     anybody
    1.17
     anyone
    1.09
     whatsoever
    1.02
     anywhere
    1.00
     ANY
    1.00
     slightest
    0.95
    Act Density 0.406%

    No Known Activations