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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahoma
    -0.16
    ovy
    -0.16
    ersist
    -0.14
    ÙĪÛĮÙĦ
    -0.14
    ибли
    -0.14
     Burke
    -0.14
    umbled
    -0.14
    icide
    -0.13
    .kwargs
    -0.13
     Sav
    -0.13
    POSITIVE LOGITS
    923
    0.16
    zon
    0.15
    arket
    0.15
    ÑĢÑĥк
    0.15
    edes
    0.14
    922
    0.14
    924
    0.14
    oles
    0.14
    arn
    0.14
    ARN
    0.14
    Act Density 0.003%

    No Known Activations