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

    Neuronpedia

    INDEX
    Explanations

    text indicating a source or reference, such as website names or citations

    oai_token-act-pair · gpt-3.5-turbo

    colons and punctuation marks indicating list-like or defined structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.70
    alog
    -0.69
     transfer
    -0.69
     tremend
    -0.68
    alysed
    -0.67
    poons
    -0.66
    orth
    -0.66
     annihil
    -0.65
    bered
    -0.64
     millennium
    -0.63
    POSITIVE LOGITS
     Provided
    0.98
     "...
    0.96
     "'
    0.92
     "âĢ¦
    0.92
     "[
    0.86
     https
    0.85
     Yeah
    0.83
     Logged
    0.81
     http
    0.80
     "@
    0.78
    Act Density 0.102%

    No Known Activations