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

    Neuronpedia

    INDEX
    Explanations

    mentions of favorite things or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    661
    -0.17
    ñana
    -0.16
    benh
    -0.15
     Mog
    -0.15
    oka
    -0.14
     Stef
    -0.14
    hec
    -0.14
     Verde
    -0.14
     Paradise
    -0.14
    isp
    -0.13
    POSITIVE LOGITS
    ENO
    0.17
    _PROVID
    0.14
    Marsh
    0.14
    گاÙĩÛĮ
    0.14
    ormal
    0.14
    ambre
    0.14
    ÑĤов
    0.13
    ock
    0.13
     )↵↵↵↵↵↵↵↵
    0.13
    egend
    0.13
    Act Density 0.056%

    No Known Activations