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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant actions, states, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ´¥
    -0.16
    елиÑĩ
    -0.15
    ULA
    -0.14
    hea
    -0.14
    partment
    -0.14
    utherland
    -0.14
    ULSE
    -0.13
    canf
    -0.13
    ért
    -0.13
    imon
    -0.13
    POSITIVE LOGITS
    isque
    0.15
     humane
    0.15
    679
    0.14
    erdale
    0.14
    wend
    0.14
     Ihr
    0.13
    uegos
    0.13
    ibaba
    0.13
    ibility
    0.13
     Lun
    0.13
    Act Density 0.087%

    No Known Activations