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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and professions, particularly politicians and miners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edo
    -0.78
    heon
    -0.63
     Ryder
    -0.62
    edom
    -0.62
     Drift
    -0.61
    ively
    -0.61
    achu
    -0.61
    ensity
    -0.61
    eva
    -0.60
    eering
    -0.60
    POSITIVE LOGITS
    heads
    0.84
    GBT
    0.82
    ishable
    0.78
    boats
    0.71
    boys
    0.71
    HEAD
    0.70
    INGTON
    0.68
    bugs
    0.67
    wash
    0.65
    field
    0.65
    Act Density 0.050%

    No Known Activations