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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ders
    -0.16
    owaÄĩ
    -0.15
    immel
    -0.15
     derp
    -0.15
    .promise
    -0.15
    owa
    -0.14
    udu
    -0.14
    ILITY
    -0.14
    .public
    -0.13
    rani
    -0.13
    POSITIVE LOGITS
    cri
    0.15
    eat
    0.15
    ub
    0.15
    emy
    0.15
     sob
    0.14
    ][/
    0.14
    -plus
    0.13
    uro
    0.13
     each
    0.13
     argument
    0.13
    Act Density 0.080%

    No Known Activations