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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating alternative scenarios

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

    introduces the alternative or default case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onedDateTime
    -0.47
    TypedDataSet
    -0.44
    ]")]
    -0.42
    righted
    -0.40
    jó
    -0.40
    Sprintf
    -0.40
    ulemon
    -0.38
    待
    -0.36
    Newspaper
    -0.35
     blister
    -0.35
    POSITIVE LOGITS
     otherwise
    1.02
    otherwise
    1.00
    Otherwise
    0.94
     Otherwise
    0.91
    httphttps
    0.86
     OTHERWISE
    0.81
     altrimenti
    0.76
     иначе
    0.69
     defaultstate
    0.66
    否则
    0.65
    Act Density 0.001%

    No Known Activations