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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating actions or characteristics in a context that suggests comparison or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assen
    -0.16
    iban
    -0.16
    atten
    -0.15
     Dread
    -0.15
    _plural
    -0.14
    ayer
    -0.14
    loquent
    -0.14
    ÙĶ
    -0.14
    \Html
    -0.14
    ÅĻiv
    -0.14
    POSITIVE LOGITS
    sam
    0.16
    ombo
    0.15
    ear
    0.15
    )null
    0.15
    tere
    0.14
     bufsize
    0.14
    anje
    0.14
    orage
    0.14
     bj
    0.14
     somewhat
    0.14
    Act Density 0.003%

    No Known Activations