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

    Neuronpedia

    INDEX
    Explanations

    the word "Or" in various formats

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

    Or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fase
    -0.59
     Benedetto
    -0.52
    IEVE
    -0.51
    transQ
    -0.50
     Analyse
    -0.49
    able
    -0.48
    Analyse
    -0.48
     Aviso
    -0.47
    amem
    -0.47
    Fase
    -0.47
    POSITIVE LOGITS
     Or
    1.66
    Or
    1.55
     or
    1.21
     OR
    1.10
     Ор
    1.02
    getOr
    0.97
     或
    0.97
    Или
    0.91
    或
    0.90
    or
    0.89
    Act Density 0.020%

    No Known Activations