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

    Neuronpedia

    INDEX
    Explanations

    comparative terms related to performance and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fo
    -0.18
    okus
    -0.17
    ink
    -0.15
    ig
    -0.15
    foy
    -0.15
    ü
    -0.14
    agt
    -0.14
     sek
    -0.13
    ag
    -0.13
    rod
    -0.13
    POSITIVE LOGITS
     THAN
    0.15
    uraa
    0.15
    edback
    0.15
    óż
    0.15
     than
    0.15
    ihan
    0.15
    clamp
    0.15
    than
    0.15
    unan
    0.14
    ÏĢο
    0.14
    Act Density 0.165%

    No Known Activations