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

    Neuronpedia

    INDEX
    Explanations

    contractions of "can not" (canâĢˆĻt) followed by a word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can't"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -0.81
     SetTextColor
    -0.64
     Gleaming
    -0.61
     continents
    -0.58
     Houses
    -0.57
     scen
    -0.56
     tremend
    -0.56
     rall
    -0.55
    soType
    -0.55
     behavi
    -0.55
    POSITIVE LOGITS
    urtle
    1.02
    weet
    0.96
    otally
    0.84
    urtles
    0.83
    ubs
    0.82
    omp
    0.82
    olkien
    0.81
    ween
    0.80
    ruly
    0.79
    ribe
    0.79
    Act Density 0.027%

    No Known Activations