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

    Neuronpedia

    INDEX
    Explanations

    specific names and identifying terms related to characters or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.18
    ÄĻż
    -0.15
    izzo
    -0.15
    ikut
    -0.14
    rios
    -0.13
    )did
    -0.13
    embro
    -0.13
    ient
    -0.12
    iversal
    -0.12
    ivery
    -0.12
    POSITIVE LOGITS
    odore
    0.21
    adays
    0.16
    HING
    0.13
     sayıda
    0.13
    alendar
    0.12
    erb
    0.12
    ácil
    0.12
    ³³³³³
    0.12
    ECH
    0.12
    داد
    0.12
    Act Density 0.461%

    No Known Activations