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

    Neuronpedia

    INDEX
    Explanations

    pattern of characters that may represent special characters or marks

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to significant numeric values or important statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulkan
    -0.76
    inyl
    -0.70
    ussian
    -0.69
     withdraw
    -0.67
    uly
    -0.67
     indistinguishable
    -0.66
     warr
    -0.64
    idation
    -0.63
    iga
    -0.63
    emort
    -0.63
    POSITIVE LOGITS
    Speaking
    0.94
    Published
    0.87
    Posted
    0.85
    SEE
    0.85
    ³³³
    0.85
    Writing
    0.82
    ccording
    0.80
    Sure
    0.79
    Seriously
    0.78
    SHARE
    0.77
    Act Density 0.531%

    No Known Activations