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

    Neuronpedia

    INDEX
    Explanations

    instances of references to transportation by a cab

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "cab"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    placed
    -0.67
     midterm
    -0.64
    imaru
    -0.63
    velength
    -0.62
     Princ
    -0.62
    perse
    -0.61
    Republic
    -0.61
     Kos
    -0.60
     Bread
    -0.60
     //[
    -0.59
    POSITIVE LOGITS
     cab
    1.19
    aret
    0.94
     corrid
    0.86
    rio
    0.82
    leton
    0.76
     Cab
    0.76
    illo
    0.70
    arella
    0.69
    riet
    0.69
    oline
    0.68
    Act Density 0.004%

    No Known Activations