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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a lack of evidence or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.66
    __':
    -0.54
    PreInfinity
    -0.52
    __':
    -0.50
    İstinadlar
    -0.49
    __":
    -0.49
     estekak
    -0.48
    әрмәләр
    -0.47
     OMS
    -0.46
    ViewFeatures
    -0.45
    POSITIVE LOGITS
     sekali
    0.58
     voire
    0.54
     posibilidades
    0.48
     žiad
    0.48
     (<
    0.47
     izquier
    0.47
    Few
    0.47
     cooperación
    0.46
     chance
    0.46
     influência
    0.46
    Act Density 0.250%

    No Known Activations