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

    Neuronpedia

    INDEX
    Explanations

    reports of violent incidents and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (&
    -0.13
    (s
    -0.13
    ãģĿãģĨãģª
    -0.13
    bsites
    -0.13
    
    -0.12
    ustria
    -0.12
    ÑĨÑĸоналÑĮ
    -0.12
    **
    -0.11
    estead
    -0.11
    toPromise
    -0.11
    POSITIVE LOGITS
    .gif
    0.19
    :///
    0.15
    qué
    0.15
    .jpg
    0.15
    isque
    0.15
    :`~
    0.14
    éĢģæĸĻçĦ¡æĸĻ
    0.14
    .JPG
    0.14
    ledon
    0.13
    istrovstvÃŃ
    0.13
    Act Density 6.155%

    No Known Activations