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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating concerns about abusive relationships and customer grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oya
    -0.17
    ndo
    -0.15
    leck
    -0.15
    nite
    -0.15
     Hairst
    -0.15
    ilim
    -0.14
    oller
    -0.14
     tar
    -0.14
    inkle
    -0.14
     mute
    -0.13
    POSITIVE LOGITS
    ize
    0.15
    uga
    0.15
    erdale
    0.15
    avan
    0.15
    PCS
    0.14
     Marsh
    0.14
    åįĴ
    0.14
     repeatedly
    0.14
    397
    0.13
    -sur
    0.13
    Act Density 0.182%

    No Known Activations