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

    Neuronpedia

    INDEX
    Explanations

    connecting words and phrases that indicate relationships or transitions in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gest
    -0.16
    xFFF
    -0.15
    \Id
    -0.14
    ipur
    -0.14
     Koh
    -0.14
    etz
    -0.14
     Chance
    -0.13
    sole
    -0.13
    alse
    -0.13
    ayla
    -0.13
    POSITIVE LOGITS
    anni
    0.16
    à¥ģड
    0.15
    orris
    0.15
    hle
    0.14
     urg
    0.13
    ahoma
    0.13
    eten
    0.13
    argin
    0.13
     Deferred
    0.13
    DefaultValue
    0.12
    Act Density 0.028%

    No Known Activations