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

    Neuronpedia

    INDEX
    Explanations

    references to natural phenomena or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "natural."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.85
    raq
    -0.76
    ammy
    -0.76
    lished
    -0.74
    blers
    -0.74
    bler
    -0.73
    rav
    -0.72
    eters
    -0.70
    Reloaded
    -0.69
    iosyncr
    -0.69
    POSITIVE LOGITS
    istic
    1.14
    ization
    1.11
    izations
    1.10
    ized
    1.07
    isation
    1.01
    izes
    1.01
    istically
    0.95
    izing
    0.92
    ised
    0.88
    ize
    0.88
    Act Density 0.023%

    No Known Activations