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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íķĺìĦ¸ìļĶ
    -0.15
    ÑĮÑĤе
    -0.15
    azzi
    -0.15
     youre
    -0.15
     ä½ł
    -0.14
    anted
    -0.14
    /***/
    -0.14
    yny
    -0.14
     belief
    -0.14
    claimer
    -0.14
    POSITIVE LOGITS
    Ah
    0.20
    FML
    0.20
     Ah
    0.20
     oh
    0.19
     wait
    0.18
    Hmm
    0.17
    wait
    0.17
     ah
    0.17
     Hmm
    0.16
    Wait
    0.16
    Act Density 0.200%

    No Known Activations