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

    Neuronpedia

    INDEX
    Explanations

    specific unicode characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.73
    agascar
    -0.69
    hander
    -0.68
    aday
    -0.65
    ifications
    -0.63
     externalToEVAOnly
    -0.62
    swick
    -0.61
    essage
    -0.61
    ativity
    -0.60
    omial
    -0.60
    POSITIVE LOGITS
    Į
    1.99
    Ľ
    1.79
    Ĵ
    1.73
    Ķ
    1.72
    ļ
    1.71
    ĥ
    1.69
    ħ
    1.68
    Ĭ
    1.65
    ½
    1.65
    ©
    1.64
    Act Density 0.014%

    No Known Activations