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

    Neuronpedia

    INDEX
    Explanations

    content related to job applications and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brill
    -0.17
    flash
    -0.17
    ikon
    -0.15
    burgh
    -0.15
     liber
    -0.15
    Flash
    -0.14
    ICON
    -0.14
     bait
    -0.14
    icon
    -0.13
    laden
    -0.13
    POSITIVE LOGITS
     reference
    0.27
     recommendation
    0.26
     letter
    0.26
     letters
    0.25
     references
    0.25
     Character
    0.23
     character
    0.23
     Reference
    0.23
    -reference
    0.23
    reference
    0.22
    Act Density 0.010%

    No Known Activations