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

    Neuronpedia

    INDEX
    Explanations

    code-related annotations and comments within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.22
    айд
    -0.17
    opolitan
    -0.15
    obs
    -0.15
    ustos
    -0.15
    ertools
    -0.15
    Ñıб
    -0.14
    loor
    -0.14
    /Form
    -0.14
    verity
    -0.14
    POSITIVE LOGITS
     Seymour
    0.17
    .mob
    0.15
    γοÏħ
    0.15
     Albert
    0.14
    734
    0.14
     Warner
    0.14
    score
    0.14
    sip
    0.14
    å¼ĺ
    0.14
    sse
    0.13
    Act Density 0.010%

    No Known Activations