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

    Neuronpedia

    INDEX
    Explanations

    conditional expressions and speculative language related to potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -1.02
    CloseOperation
    -0.93
    OrBuilder
    -0.87
    WebVitals
    -0.86
     EconPapers
    -0.84
    DockStyle
    -0.84
    ActivityCompat
    -0.82
     beginnetje
    -0.79
    InputBorder
    -0.77
    Personensuche
    -0.77
    POSITIVE LOGITS
    ……
    0.52
    čo
    0.48
    ......
    0.46
    …..
    0.46
     sp
    0.45
    rikan
    0.44
    .....
    0.43
    ….
    0.42
    Class
    0.42
    …….
    0.42
    Act Density 0.056%

    No Known Activations