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

    Neuronpedia

    INDEX
    Explanations

    terms related to interaction and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wik
    -0.15
    egade
    -0.15
    ongs
    -0.15
    venir
    -0.15
    osu
    -0.15
    jours
    -0.15
    ping
    -0.15
    ạp
    -0.14
    estatus
    -0.14
    окÑĢем
    -0.14
    POSITIVE LOGITS
    ives
    0.19
    uality
    0.19
    ivate
    0.18
    ative
    0.17
    å¼ı
    0.17
    uator
    0.17
    ively
    0.16
    iveness
    0.16
    ype
    0.16
    ÅĽÄĩ
    0.16
    Act Density 0.018%

    No Known Activations