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

    Neuronpedia

    INDEX
    Explanations

    reasons for actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate reasons or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.72
    aith
    -0.71
    ikan
    -0.69
    rop
    -0.66
    ãĤ¹
    -0.65
    thal
    -0.64
    ko
    -0.63
    ized
    -0.63
    Sky
    -0.62
    ãĤ¤ãĥĪ
    -0.62
    POSITIVE LOGITS
    soever
    0.83
    soType
    0.83
    isSpecialOrderable
    0.75
     why
    0.73
    iatus
    0.72
    abouts
    0.69
    Origin
    0.69
    orsi
    0.67
    ricanes
    0.67
     exists
    0.63
    Act Density 0.025%

    No Known Activations