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

    Neuronpedia

    INDEX
    Explanations

    references to resources and their associated costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Winds
    -0.15
     Tobacco
    -0.14
    -wrapper
    -0.13
    tsky
    -0.13
    igar
    -0.13
     Spice
    -0.13
    enas
    -0.12
    à¹Ĥà¸ģ
    -0.12
    _ti
    -0.12
    ضÙĬ
    -0.12
    POSITIVE LOGITS
     water
    0.92
     Water
    0.76
    water
    0.73
    Water
    0.70
     WATER
    0.66
    æ°´
    0.66
    -water
    0.63
    _water
    0.61
     agua
    0.59
    .water
    0.55
    Act Density 0.007%

    No Known Activations