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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a generalization or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orns
    -0.17
    inja
    -0.16
    idis
    -0.15
    ẻ
    -0.15
    nap
    -0.15
    ipur
    -0.14
    ngör
    -0.14
    essim
    -0.14
    edic
    -0.14
    inya
    -0.14
    POSITIVE LOGITS
    -called
    0.20
     exh
    0.17
    jaw
    0.17
    CKET
    0.16
    aft
    0.15
     far
    0.15
    aking
    0.14
     eff
    0.14
    il
    0.14
     benign
    0.13
    Act Density 0.037%

    No Known Activations