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

    Neuronpedia

    INDEX
    Explanations

    keywords related to aquatic life, particularly fish

    oai_token-act-pair · gpt-3.5-turbo

    references to fish in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FINE
    -0.69
    rian
    -0.66
    DOS
    -0.61
    uler
    -0.61
    OWN
    -0.60
    itzer
    -0.60
     Despair
    -0.60
    éĹ
    -0.60
     condem
    -0.59
    GV
    -0.59
    POSITIVE LOGITS
    bowl
    1.40
    mong
    1.19
    meal
    1.07
    nets
    1.03
    hook
    1.00
    tails
    1.00
    fish
    0.98
    tail
    0.96
    lings
    0.94
    tailed
    0.94
    Act Density 0.037%

    No Known Activations