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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    actions or verbs associated with taking initiative or performing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emonic
    -0.74
    è¦ļéĨĴ
    -0.73
    heit
    -0.69
    urus
    -0.69
    uras
    -0.68
    ertodd
    -0.67
    aghan
    -0.67
    Cas
    -0.66
    itta
    -0.66
    inus
    -0.65
    POSITIVE LOGITS
     tomorrow
    1.08
     hereafter
    0.96
     anytime
    0.88
     soon
    0.88
     someday
    0.84
     whatever
    0.82
     whoever
    0.80
     whichever
    0.78
     forever
    0.77
     next
    0.75
    Act Density 0.407%

    No Known Activations