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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to approval and endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĨе
    -0.16
    ums
    -0.15
    -browser
    -0.15
     Erotik
    -0.15
    ings
    -0.15
    ennis
    -0.14
    olicit
    -0.14
    oidal
    -0.14
    wig
    -0.14
    gow
    -0.14
    POSITIVE LOGITS
    ably
    0.22
    ance
    0.21
    /dis
    0.20
    able
    0.18
    ANCE
    0.18
    amet
    0.15
    imated
    0.15
    exion
    0.15
    ances
    0.15
    emale
    0.15
    Act Density 0.017%

    No Known Activations