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

    Neuronpedia

    INDEX
    Explanations

    specific names or titles, particularly related to media or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PARATOR
    -0.16
    sworth
    -0.15
    ELLOW
    -0.15
    าà¸į
    -0.15
    ë§ŀ
    -0.14
    rift
    -0.14
    unsch
    -0.14
    oui
    -0.14
    ENARIO
    -0.14
    tempts
    -0.14
    POSITIVE LOGITS
    ed
    0.16
     sensible
    0.15
    arpa
    0.15
    ter
    0.15
    do
    0.14
    sie
    0.14
    _advanced
    0.14
     Singles
    0.14
    uppet
    0.14
    educt
    0.14
    Act Density 0.116%

    No Known Activations