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

    Neuronpedia

    INDEX
    Explanations

    terms related to return policies and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    let
    -0.15
     Merlin
    -0.15
     pr
    -0.15
    erno
    -0.14
    omet
    -0.14
    æł
    -0.14
    κÏĦή
    -0.14
    nds
    -0.14
    ignon
    -0.13
     ple
    -0.13
    POSITIVE LOGITS
    estroy
    0.16
    iggs
    0.15
    egend
    0.15
    servername
    0.14
    ¹
    0.14
    edo
    0.14
    ocale
    0.14
    mazon
    0.14
    erer
    0.14
    éĢļ
    0.14
    Act Density 0.013%

    No Known Activations