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

    Neuronpedia

    INDEX
    Explanations

    terms related to neutrality or neutral characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continente
    -0.59
    х
    -0.54
    flix
    -0.51
    antasy
    -0.48
     فق
    -0.47
    ิลป
    -0.46
    ijão
    -0.46
    upol
    -0.46
    mado
    -0.46
    dart
    -0.45
    POSITIVE LOGITS
     neutral
    1.08
     Neutral
    1.06
    neutral
    0.94
    Neutral
    0.92
     neutre
    0.85
    Personensuche
    0.83
    preview
    0.81
    SequentialGroup
    0.80
    AccessorTable
    0.80
     preview
    0.76
    Act Density 0.091%

    No Known Activations