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

    Neuronpedia

    INDEX
    Explanations

    references to names and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alist
    -0.18
    ÎĦ
    -0.15
    ingers
    -0.14
    abh
    -0.14
    ano
    -0.14
    ersh
    -0.14
     Licht
    -0.14
    pty
    -0.14
    .gov
    -0.13
    ullo
    -0.13
    POSITIVE LOGITS
     Bender
    0.15
    plate
    0.15
    /name
    0.15
     names
    0.14
    erture
    0.14
    uggage
    0.13
    à¥Ĥद
    0.13
    аÑĢамеÑĤ
    0.13
     plate
    0.13
    污
    0.13
    Act Density 0.100%

    No Known Activations