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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the themes of popularity and character dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athon
    -0.15
    ipse
    -0.14
    اÙĦÙĦÙĩ
    -0.14
    ipo
    -0.14
    sto
    -0.13
    utton
    -0.13
    .PR
    -0.13
     Grinder
    -0.13
    ILLE
    -0.13
    orno
    -0.13
    POSITIVE LOGITS
     examples
    0.23
     example
    0.22
     Examples
    0.21
    Examples
    0.21
     exemple
    0.19
    ä¾ĭ
    0.19
     exemp
    0.18
     exemplo
    0.18
    -example
    0.17
    examples
    0.17
    Act Density 0.306%

    No Known Activations