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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     substance
    -0.14
    ungeons
    -0.14
    ĺ
    -0.14
     congen
    -0.14
    wand
    -0.14
    emy
    -0.14
    .anim
    -0.14
     Ñģвид
    -0.14
    /***/
    -0.14
    èle
    -0.13
    POSITIVE LOGITS
    erap
    0.16
    atorial
    0.16
    eken
    0.14
    аÑĩе
    0.14
    egal
    0.14
    abajo
    0.14
    ecess
    0.14
    AYOUT
    0.14
    ekim
    0.14
    inded
    0.14
    Act Density 0.067%

    No Known Activations