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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal or health-related terms indicating serious circumstances or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fieldNum
    -0.60
    AndEndTag
    -0.44
     Billie
    -0.44
    IMIENTO
    -0.44
     Borne
    -0.43
     Sush
    -0.43
     Weich
    -0.43
    asable
    -0.43
     Libya
    -0.42
     Warbler
    -0.42
    POSITIVE LOGITS
    ated
    1.05
    ating
    1.04
    ATED
    0.79
    ATING
    0.79
    rated
    0.71
    ate
    0.71
    ates
    0.67
    rating
    0.61
    ATES
    0.60
    ATE
    0.59
    Act Density 0.427%

    No Known Activations