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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to technology and programming

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thal
    -0.69
    ĪĴ
    -0.67
    ĵĺ
    -0.67
    ims
    -0.66
    ħĭ
    -0.65
    ibilities
    -0.65
    estial
    -0.63
    ogun
    -0.62
     sleeves
    -0.62
     seams
    -0.59
    POSITIVE LOGITS
     ours
    0.77
    76561
    0.72
    worth
    0.71
    mma
    0.70
    dropping
    0.70
    cape
    0.67
    giving
    0.66
    ablishment
    0.63
    calling
    0.63
     "+
    0.63
    Act Density 0.066%

    No Known Activations