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

    Neuronpedia

    INDEX
    Explanations

    instances of logical reasoning and examples used to support arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icerca
    -0.17
    #,
    -0.16
     (),
    -0.15
    amu
    -0.15
    ones
    -0.15
    okit
    -0.14
     коÑĤоÑĢÑĥÑİ
    -0.14
    antom
    -0.14
     "*",
    -0.14
    ि,
    -0.14
    POSITIVE LOGITS
    —and
    0.15
    /if
    0.15
    –and
    0.14
     же
    0.14
    forth
    0.14
    æĿ¥è¯´
    0.14
    á»ijc
    0.14
     unlike
    0.14
    (and
    0.14
    m
    0.13
    Act Density 0.236%

    No Known Activations