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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names that could be related to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    specific names and references, particularly related to people, products, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gd
    -0.92
     Howell
    -0.92
     McL
    -0.82
    GD
    -0.78
     McInt
    -0.77
     Whit
    -0.77
     Gillespie
    -0.75
    ink
    -0.74
    agin
    -0.74
    ieg
    -0.73
    POSITIVE LOGITS
    RA
    1.72
     RA
    1.61
    ra
    1.60
     Kra
    1.38
     ra
    1.29
    Ra
    1.26
     Ara
    1.26
     Ra
    1.19
     Rai
    1.18
     Hera
    1.08
    Act Density 0.372%

    No Known Activations