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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate typical or normal behavior

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

    typically, normally, usually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verification
    -0.49
     hjælp
    -0.47
    HKEY
    -0.46
     skär
    -0.44
    存于互联网档案馆
    -0.43
     hendes
    -0.43
     BoxFit
    -0.43
     hjelp
    -0.43
     spørs
    -0.42
     inscrição
    -0.42
    POSITIVE LOGITS
     typically
    0.99
    typically
    0.95
     normally
    0.91
    Typically
    0.90
     usually
    0.90
     Typically
    0.89
    normally
    0.88
     Normally
    0.83
    usually
    0.82
     Usually
    0.79
    Act Density 0.026%

    No Known Activations