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

    Neuronpedia

    INDEX
    Explanations

    multi-word phrases with each word starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sentences with high numerical values or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .""
    -0.85
    ',"
    -0.81
    ,'"
    -0.69
    '."
    -0.68
    uilt
    -0.65
    )].
    -0.64
    ividual
    -0.64
    ij士
    -0.62
    lished
    -0.60
    irlf
    -0.60
    POSITIVE LOGITS
    ↵
    1.73
    ↵↵
    1.18
    <|endoftext|>
    1.09
    SPONSORED
    0.86
    ↵Âł
    0.82
     However
    0.66
    pmwiki
    0.65
     Unfortunately
    0.63
     Alternatively
    0.63
     behavi
    0.62
    Act Density 1.827%

    No Known Activations