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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and entities along with their associated roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìļ°
    -0.17
    Äįan
    -0.15
    /fs
    -0.14
    Naz
    -0.14
    puties
    -0.14
    arine
    -0.14
    amina
    -0.14
     subpoena
    -0.14
    ourg
    -0.13
    ết
    -0.13
    POSITIVE LOGITS
    196
    0.24
    197
    0.20
    195
    0.18
    198
    0.17
     Laugh
    0.16
    ï¼ĪæĺŃåĴĮ
    0.16
     Lands
    0.15
    @qq
    0.15
     independently
    0.15
     USSR
    0.15
    Act Density 0.234%

    No Known Activations