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

    Neuronpedia

    INDEX
    Explanations

    code snippets and function definitions related to settings and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stanton
    -0.16
    İ
    -0.14
    arken
    -0.14
     Gardner
    -0.14
     Quint
    -0.14
     bordel
    -0.13
     polarization
    -0.13
    ï¼»
    -0.13
    Ĵ
    -0.13
    erno
    -0.13
    POSITIVE LOGITS
    uzzi
    0.17
    orrh
    0.15
    VICE
    0.14
    -fluid
    0.14
     Emblem
    0.14
    ãģĭãĤı
    0.14
     fluid
    0.14
    CCR
    0.14
    prit
    0.14
    uber
    0.13
    Act Density 0.112%

    No Known Activations