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

    Neuronpedia

    INDEX
    Explanations

    important or impactful concepts related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.16
    IGINAL
    -0.15
    ople
    -0.15
    oq
    -0.15
    oton
    -0.15
    .AutoScaleMode
    -0.14
    edException
    -0.14
    wards
    -0.14
    tings
    -0.14
    liness
    -0.14
    POSITIVE LOGITS
    egrity
    0.17
     portions
    0.15
     ********************************************************************************
    0.15
    ately
    0.15
    /key
    0.15
    ãĥ£
    0.14
     sayıda
    0.14
    hetto
    0.14
    reed
    0.14
     ölçüde
    0.14
    Act Density 0.037%

    No Known Activations