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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Filmografie
    -0.64
     CallOverrides
    -0.59
    estries
    -0.57
    ³/
    -0.56
    getDoctrine
    -0.56
    ötet
    -0.55
     Brack
    -0.55
     makeStyles
    -0.55
    $.}
    -0.54
    UnifiedTopology
    -0.54
    POSITIVE LOGITS
    abc
    0.87
     ABC
    0.85
     abc
    0.83
    ABC
    0.77
    ABCDEF
    0.73
    qrstuvwxyz
    0.70
    abcd
    0.69
     xyz
    0.68
    XYZ
    0.67
     ABCD
    0.66
    Act Density 0.518%

    No Known Activations