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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions and clarifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    URLException
    -0.60
    queryInterface
    -0.59
    autique
    -0.57
    andExpect
    -0.56
    IVEREF
    -0.56
    mergeFrom
    -0.54
    TabStop
    -0.50
    ActionEvent
    -0.50
    UnknownFieldSet
    -0.48
    WarningLevel
    -0.47
    POSITIVE LOGITS
    FYI
    0.69
     FYI
    0.68
    APOLIS
    0.62
    úsqueda
    0.61
     Perlu
    0.61
    euw
    0.60
    wikkeld
    0.59
     Larissa
    0.58
    RTGC
    0.56
    abou
    0.55
    Act Density 0.024%

    No Known Activations