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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating caution or warnings

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

    watch out or beware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.48
    enderror
    -0.45
    KommentareTeilen
    -0.44
    setOnAction
    -0.42
     kecamatan
    -0.40
    ดำ
    -0.40
     Chwiliwch
    -0.40
     labios
    -0.40
     EnglishChoose
    -0.39
     oídos
    -0.39
    POSITIVE LOGITS
     lookout
    0.61
     Lookout
    0.60
     warning
    0.57
    Cuidado
    0.53
    GIVEREF
    0.52
     Warning
    0.51
     beware
    0.50
    toThrow
    0.50
     ALERT
    0.49
    warning
    0.48
    Act Density 0.003%

    No Known Activations