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

    Neuronpedia

    INDEX
    Explanations

    terms related to revealing secrets or uncovering mysteries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رÙĪز
    -0.16
    ckett
    -0.15
    unfinished
    -0.15
    ä¸į足
    -0.15
    	Copyright
    -0.15
    ä»ĺãģij
    -0.14
    inou
    -0.14
    vern
    -0.14
    qli
    -0.14
    èµ·
    -0.14
    POSITIVE LOGITS
    ing
    0.21
     mysteries
    0.19
    (Un
    0.19
     secrets
    0.17
    ning
    0.17
    ear
    0.17
     hidden
    0.16
    æŀIJ
    0.16
    stan
    0.16
     khá»ıi
    0.15
    Act Density 0.034%

    No Known Activations