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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or acknowledgment of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "existence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gar
    -0.68
     shoulders
    -0.65
     Athletic
    -0.61
    Sen
    -0.61
    geon
    -0.61
    jer
    -0.60
    eric
    -0.60
    otto
    -0.60
    mor
    -0.59
    cise
    -0.59
    POSITIVE LOGITS
     existence
    1.00
    istence
    0.93
    nces
    0.84
    uality
    0.82
     existed
    0.80
    entially
    0.80
    chool
    0.79
    ality
    0.78
     incarn
    0.78
     exists
    0.78
    Act Density 0.007%

    No Known Activations