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

    Neuronpedia

    INDEX
    Explanations

    timestamps and update information in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aux
    -0.17
    linger
    -0.16
    erner
    -0.15
    ìĦľëĬĶ
    -0.15
    ominator
    -0.15
    azzi
    -0.15
    oyer
    -0.15
    ī
    -0.14
    erm
    -0.14
    еÑĤелÑĮ
    -0.14
    POSITIVE LOGITS
     version
    0.16
     story
    0.16
     numbers
    0.16
     Mon
    0.15
     guidance
    0.15
    td
    0.15
    ysl
    0.15
    lys
    0.14
    çīĪ
    0.14
     almost
    0.14
    Act Density 0.007%

    No Known Activations