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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of unnecessary actions or redundancies

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

    statements of fact or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DC
    -0.47
     imprison
    -0.45
    Yogurt
    -0.43
    FBI
    -0.43
     Arora
    -0.42
    JSON
    -0.41
    werkstatt
    -0.41
     Administrativna
    -0.40
    HPV
    -0.40
    ERC
    -0.40
    POSITIVE LOGITS
    Needless
    1.70
     Needless
    1.70
     needless
    1.51
     naturligt
    0.75
    PreferredItem
    0.68
     Naturally
    0.66
    Naturally
    0.65
    obviously
    0.65
     Obviously
    0.64
     évidemment
    0.63
    Act Density 0.002%

    No Known Activations