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

    Neuronpedia

    INDEX
    Explanations

    occurrences of non-zero numerical values or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hdashline
    -0.46
    KURZBESCHREIBUNG
    -0.44
    "}\
    -0.44
    strip
    -0.43
     reac
    -0.41
     strip
    -0.40
    )}+
    -0.40
    >",
    -0.40
     dial
    -0.39
     Dri
    -0.38
    POSITIVE LOGITS
     masiva
    0.54
    0.52
    InjectAttribute
    0.48
    ьаж
    0.48
    flores
    0.46
     propOrder
    0.44
     برانيه
    0.44
     Audiodateien
    0.44
    crollView
    0.44
    цездатний
    0.43
    Act Density 0.385%

    No Known Activations