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

    Neuronpedia

    INDEX
    Explanations

    evaluative descriptions of writing quality and style

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.16
     span
    -0.16
    board
    -0.15
    -0.15
    itori
    -0.14
    op
    -0.14
     Stap
    -0.14
     |_
    -0.14
     cr
    -0.14
    elled
    -0.14
    POSITIVE LOGITS
    æııè¿°
    0.16
    ãĤµãĥ¼
    0.15
    ongoose
    0.15
    LIKELY
    0.15
    ông
    0.15
     Qed
    0.15
    راÙĤ
    0.15
    ONGL
    0.14
     fitte
    0.14
    WRAPPER
    0.14
    Act Density 0.118%

    No Known Activations