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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alphabet
    -0.16
    ISIBLE
    -0.15
    uhe
    -0.15
     alphabet
    -0.14
     adını
    -0.14
    rientation
    -0.14
    OperationException
    -0.14
    alphabet
    -0.13
     ÑĪлÑıÑħ
    -0.13
    tera
    -0.13
    POSITIVE LOGITS
     usage
    0.23
     Usage
    0.22
    Usage
    0.21
     sentence
    0.21
    usage
    0.19
    gram
    0.19
    USAGE
    0.19
     USAGE
    0.19
     construction
    0.19
     col
    0.19
    Act Density 0.068%

    No Known Activations