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

    Neuronpedia

    INDEX
    Explanations

    terms related to automated or automatic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or scientific terminology related to computational or systematic processes.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     valentín
    -0.47
     suprême
    -0.47
    crí
    -0.45
    ądź
    -0.45
     Inscrivez
    -0.42
     león
    -0.42
     Haush
    -0.42
     aislado
    -0.41
     âme
    -0.41
     duquel
    -0.40
    POSITIVE LOGITS
     automatic
    0.87
     automatically
    0.84
     Automatically
    0.82
    automatic
    0.82
     AUTOMATIC
    0.80
     Automatic
    0.79
    automatically
    0.79
    Automatic
    0.75
     naturally
    0.73
    naturally
    0.73
    Act Density 0.297%

    No Known Activations