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

    Neuronpedia

    INDEX
    Explanations

    negative character assessments and disparaging remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .cleanup
    -0.16
    ptive
    -0.15
    ico
    -0.15
    aza
    -0.15
    uro
    -0.15
    acted
    -0.14
    otropic
    -0.14
    .VideoCapture
    -0.14
     Levine
    -0.14
    ved
    -0.14
    POSITIVE LOGITS
    Breadcrumb
    0.16
    bens
    0.15
    ãģĭãģij
    0.15
     Rud
    0.14
     McCart
    0.14
    muz
    0.14
     cast
    0.14
    ordion
    0.13
    eden
    0.13
    imir
    0.13
    Act Density 0.214%

    No Known Activations