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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to high-intensity situations or moments

    oai_token-act-pair · gpt-3.5-turbo

    references to climbing activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.85
    fold
    -0.79
    VERTIS
    -0.73
    Ô
    -0.73
    DOS
    -0.70
     è£ı
    -0.69
     Painter
    -0.66
     Pacers
    -0.66
     Gutenberg
    -0.66
     Mour
    -0.65
    POSITIVE LOGITS
     clim
    0.98
    acter
    0.95
    actic
    0.88
     corrid
    0.87
    bers
    0.82
    ber
    0.82
     climbers
    0.79
    acus
    0.75
    byss
    0.75
    bage
    0.73
    Act Density 0.014%

    No Known Activations