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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cooking

    oai_token-act-pair · gpt-3.5-turbo

    references to the cooking process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abuse
    -0.82
    oter
    -0.77
    antage
    -0.75
    uther
    -0.74
    alter
    -0.73
    uyomi
    -0.71
    gap
    -0.70
    allows
    -0.69
     poles
    -0.69
    issues
    -0.68
    POSITIVE LOGITS
     cooked
    0.90
     hatched
    0.80
    luaj
    0.76
    ãĥĥãĤ¯
    0.75
    blooded
    0.75
    \\\\\\\\
    0.74
    ãĤ´ãĥ³
    0.71
    swick
    0.71
    ãĥ¼ãĤ¯
    0.69
    nesday
    0.69
    Act Density 0.016%

    No Known Activations