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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accessibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.77
    ortium
    -0.71
    neg
    -0.70
    conn
    -0.67
    storms
    -0.66
    origin
    -0.66
    aldi
    -0.65
    chief
    -0.65
    cius
    -0.63
    row
    -0.63
    POSITIVE LOGITS
    ibility
    1.09
    ible
    0.95
    accessible
    0.90
     accessible
    0.86
    ibly
    0.81
    isable
    0.77
     inaccessible
    0.73
    izable
    0.73
    idges
    0.69
    ahime
    0.69
    Act Density 0.014%

    No Known Activations