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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.52
     Nähe
    -0.46
     defaultdict
    -0.44
     później
    -0.43
     elsewhere
    -0.42
     riferimento
    -0.42
    vodu
    -0.41
     buurt
    -0.41
    ,
    -0.40
     kész
    -0.40
    POSITIVE LOGITS
    msgTypes
    0.85
     nakalista
    0.83
    :+:
    0.83
    tvguidetime
    0.83
    ArgsConstructor
    0.77
     StatefulWidget
    0.77
    NOPQRST
    0.76
    __":
    0.73
    TagMode
    0.72
    ientí
    0.71
    Act Density 0.596%

    No Known Activations