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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    possessive noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.73
    сылкі
    -0.70
     oprot
    -0.66
    Datuak
    -0.59
    thâu
    -0.58
     дописавши
    -0.56
    IntoConstraints
    -0.54
     ब्रेकडाउन
    -0.54
    WebElementEntity
    -0.54
     iprot
    -0.53
    POSITIVE LOGITS
     brief
    0.42
    crose
    0.39
    badah
    0.39
     course
    0.38
     lifecycle
    0.36
    pgp
    0.35
     journey
    0.35
    jwa
    0.35
     career
    0.35
     consultation
    0.34
    Act Density 0.046%

    No Known Activations