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

    Neuronpedia

    INDEX
    Explanations

    phrases that prompt critical thinking or consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecycle
    -0.16
    arness
    -0.15
    лÑĥ
    -0.14
    اÙĦØ´
    -0.14
    kker
    -0.14
    owan
    -0.14
    άνÏī
    -0.14
     Hacker
    -0.13
    hait
    -0.13
    ãĤ¸ãĤ¢
    -0.13
    POSITIVE LOGITS
     yourself
    0.16
    ance
    0.15
    593
    0.14
    hra
    0.14
    inge
    0.14
    567
    0.14
    672
    0.14
    htdocs
    0.13
    /Set
    0.13
    tout
    0.13
    Act Density 0.092%

    No Known Activations