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

    Neuronpedia

    INDEX
    Explanations

    entities with names or phrases that contain the characters "Ga"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Gaussian distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.78
    FACE
    -0.74
    PORT
    -0.73
    sburgh
    -0.72
    ty
    -0.71
    enance
    -0.70
    TY
    -0.69
    LEASE
    -0.68
    Ö¼
    -0.68
    ACTED
    -0.65
    POSITIVE LOGITS
    ither
    1.15
    vernment
    1.14
    keye
    1.06
    Ga
    1.01
    ussian
    0.97
    pless
    0.95
     Ga
    0.85
    uss
    0.84
    illard
    0.81
    urd
    0.79
    Act Density 0.034%

    No Known Activations