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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different actions or events in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    negations or terms related to denial and the impact of various factors on situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.70
    onnaissance
    -0.68
     Sud
    -0.64
    IZE
    -0.64
    stellar
    -0.63
    Ur
    -0.62
     Lud
    -0.62
    selage
    -0.62
    hin
    -0.62
     successors
    -0.61
    POSITIVE LOGITS
     inherently
    0.79
    MODE
    0.77
    Ń·
    0.76
     perme
    0.74
     decriminal
    0.73
     compulsory
    0.72
     traditionally
    0.72
     abound
    0.71
     perv
    0.70
     trump
    0.69
    Act Density 0.609%

    No Known Activations