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

    Neuronpedia

    INDEX
    Explanations

    mentions of research findings and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İ
    -0.16
    roc
    -0.15
    lec
    -0.15
    наÑĢÑĥж
    -0.15
     Monad
    -0.14
    iro
    -0.14
    Leod
    -0.14
    worth
    -0.14
    oria
    -0.14
    ump
    -0.13
    POSITIVE LOGITS
    /results
    0.15
    uras
    0.15
    缼
    0.14
    .gs
    0.14
    odox
    0.14
    磨
    0.14
    ponge
    0.14
    âĶĺ
    0.13
     sup
    0.13
     Otherwise
    0.13
    Act Density 0.026%

    No Known Activations