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

    Neuronpedia

    INDEX
    Explanations

    words associated with counting or keeping track of something

    oai_token-act-pair · gpt-3.5-turbo

    references to tallying or counting events and instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.69
     assail
    -0.62
    hov
    -0.62
     relations
    -0.62
     interrogation
    -0.62
     intervention
    -0.60
     interrog
    -0.59
     cultiv
    -0.59
    ©¶æ
    -0.59
    avage
    -0.59
    POSITIVE LOGITS
    enance
    0.81
    sung
    0.79
    ilus
    0.79
     tally
    0.78
    ming
    0.78
    alled
    0.77
     totals
    0.77
    sheet
    0.75
    STAT
    0.75
    ries
    0.74
    Act Density 0.031%

    No Known Activations