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

    Neuronpedia

    INDEX
    Explanations

    references to significant elements in narratives or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thorn
    -0.17
    idders
    -0.16
     Tay
    -0.16
    oga
    -0.14
     Lug
    -0.14
    oy
    -0.14
    hod
    -0.14
    estate
    -0.13
    atori
    -0.13
     specialist
    -0.13
    POSITIVE LOGITS
    -fontawesome
    0.17
    ân
    0.16
    chemas
    0.15
     uncomment
    0.15
    ledon
    0.14
    anism
    0.14
    ÅĽÄĩ
    0.14
    ople
    0.14
    _DETECT
    0.14
    ocom
    0.13
    Act Density 0.010%

    No Known Activations