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

    Neuronpedia

    INDEX
    Explanations

    phrases related to finality or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernes
    -0.15
    çİĩ
    -0.15
    oenix
    -0.14
    thing
    -0.14
    quez
    -0.14
    gow
    -0.14
    ophone
    -0.14
    quence
    -0.14
    ÌĨ
    -0.13
    939
    -0.13
    POSITIVE LOGITS
    ocrine
    0.23
    /end
    0.20
    ereço
    0.19
    owment
    0.19
    urance
    0.18
    angered
    0.17
    ward
    0.17
    ocrin
    0.17
    reds
    0.17
    iw
    0.17
    Act Density 0.096%

    No Known Activations