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

    Neuronpedia

    INDEX
    Explanations

    phrase repetitions indicating alternatives or combinations

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

    either one or both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.56
    Autoritní
    -0.48
    apal
    -0.47
    BibitemShut
    -0.47
    ctile
    -0.47
    ロウィン
    -0.46
    MBOL
    -0.46
    medriver
    -0.46
    madonna
    -0.46
    unsqueeze
    -0.45
    POSITIVE LOGITS
    Both
    0.45
    OGND
    0.43
    both
    0.42
     both
    0.41
    şört
    0.41
     ambas
    0.39
     Both
    0.39
    EndGlobalSection
    0.38
     BOTH
    0.36
     ambos
    0.36
    Act Density 0.013%

    No Known Activations