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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    sequences or variations of a specific character pattern in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.78
     Hemisphere
    -0.61
     destro
    -0.59
     crisis
    -0.58
    anwhile
    -0.57
     cortex
    -0.57
    iasco
    -0.57
    faced
    -0.56
     hardship
    -0.55
    matched
    -0.55
    POSITIVE LOGITS
     Sabha
    0.71
    ij士
    0.70
     Daw
    0.68
    rat
    0.67
    omer
    0.67
    ULT
    0.66
    ctive
    0.65
    KY
    0.65
    omics
    0.63
    ale
    0.62
    Act Density 0.164%

    No Known Activations