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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to characteristics or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĭ
    -0.16
    ÑĥÑĪ
    -0.15
    ë§ī
    -0.14
    TokenType
    -0.14
     bob
    -0.14
    filer
    -0.13
     gad
    -0.13
     drum
    -0.13
    }}],↵
    -0.13
    beat
    -0.13
    POSITIVE LOGITS
    umin
    0.15
    té
    0.15
    vant
    0.14
    argon
    0.14
    ume
    0.14
    onas
    0.14
    ãĥĨãĥ«
    0.14
    .promise
    0.14
    KHR
    0.13
    iddle
    0.13
    Act Density 0.019%

    No Known Activations