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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating change or movement happening in the future

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.62
    @#&
    -0.61
    CHA
    -0.59
    Wan
    -0.58
    ilon
    -0.57
    yrics
    -0.56
    agall
    -0.55
    urus
    -0.54
    itaire
    -0.54
    odor
    -0.52
    POSITIVE LOGITS
     someday
    1.74
     tomorrow
    1.68
     hereafter
    1.55
     anytime
    1.41
     soon
    1.36
    morrow
    1.24
     tonight
    1.18
     next
    1.16
     sometime
    1.14
    soon
    1.10
    Act Density 0.652%

    No Known Activations