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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the size, intensity, or significance of something

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that emphasize seriousness or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utics
    -0.84
    orthy
    -0.83
    ONSORED
    -0.76
    IER
    -0.69
    yi
    -0.65
    Tickets
    -0.65
    udder
    -0.65
    Reviewed
    -0.65
    arate
    -0.64
    INE
    -0.63
    POSITIVE LOGITS
    est
    1.15
    liest
    1.13
    ness
    1.12
     nature
    1.05
    nesses
    0.86
     possibility
    0.80
     assumption
    0.77
     portion
    0.76
     aftermath
    0.76
     ramifications
    0.76
    Act Density 0.354%

    No Known Activations