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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Skid."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     merc
    -0.67
     bulb
    -0.63
     canal
    -0.58
    È
    -0.57
     DRAG
    -0.56
    hower
    -0.54
     Ae
    -0.53
    ACTED
    -0.52
     scorp
    -0.52
     corpus
    -0.52
    POSITIVE LOGITS
    addle
    0.89
    ulkan
    0.82
    ishers
    0.77
    bucks
    0.76
    otos
    0.75
    rote
    0.74
    neys
    0.73
    rogram
    0.70
    punk
    0.70
    mitt
    0.70
    Act Density 0.070%

    No Known Activations