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

    Neuronpedia

    INDEX
    Explanations

    references to scientific or unethical experimentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    368
    -0.16
    811
    -0.15
    åĪĽæĸ°
    -0.15
    INES
    -0.15
    ascript
    -0.14
    alien
    -0.14
    iale
    -0.14
    ethyst
    -0.14
    elden
    -0.14
    _GPU
    -0.14
    POSITIVE LOGITS
     allied
    0.18
     siding
    0.17
     imprison
    0.17
     defect
    0.16
     ban
    0.16
     brain
    0.16
     seper
    0.16
     tort
    0.16
    alse
    0.16
    åĽ
    0.16
    Act Density 0.163%

    No Known Activations