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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "spike" with varying strengths of activation depending on the context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spike" and its variations, indicating fluctuations or increases in intensity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İ
    -0.71
     countryside
    -0.68
    bis
    -0.66
    mate
    -0.62
    Ĵ
    -0.62
    ACTED
    -0.62
    voc
    -0.61
    ########
    -0.60
     Incarnation
    -0.60
     Space
    -0.59
    POSITIVE LOGITS
    balls
    0.79
     spike
    0.78
     spikes
    0.75
    ilight
    0.75
    isson
    0.72
    ilant
    0.70
    rings
    0.69
    steen
    0.67
    olicy
    0.67
    lar
    0.67
    Act Density 0.011%

    No Known Activations