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

    Neuronpedia

    INDEX
    Explanations

    words or phrases containing the substring "Id"

    oai_token-act-pair · gpt-3.5-turbo

    instances of identifiers and tags or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.87
    olicy
    -0.71
    Thumbnail
    -0.71
     Ago
    -0.64
    drawn
    -0.63
     furthe
    -0.61
    å¹
    -0.61
     passer
    -0.60
    é¾
    -0.60
    istas
    -0.58
    POSITIVE LOGITS
    REDACTED
    0.72
    una
    0.68
    utive
    0.66
     Orig
    0.64
    utsche
    0.64
     Amin
    0.63
    orno
    0.63
    ANCE
    0.62
    itability
    0.61
    iru
    0.61
    Act Density 0.144%

    No Known Activations