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

    Neuronpedia

    INDEX
    Explanations

    numerical data and performance metrics related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç±
    -0.15
    ç¯
    -0.15
    ilians
    -0.15
    kie
    -0.15
    TS
    -0.14
    onis
    -0.14
    on
    -0.14
    ien
    -0.14
     Dra
    -0.14
    qa
    -0.14
    POSITIVE LOGITS
    asher
    0.18
    abh
    0.16
    woord
    0.16
    volution
    0.15
     Warfare
    0.15
    ç¥
    0.15
    nah
    0.14
    roje
    0.14
    .oc
    0.14
    emat
    0.14
    Act Density 0.004%

    No Known Activations