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

    Neuronpedia

    INDEX
    Explanations

    references to safety and security concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okoj
    -0.14
    Backing
    -0.14
    yas
    -0.14
    iqueta
    -0.14
    nte
    -0.14
    ENCIL
    -0.13
     verze
    -0.13
    away
    -0.13
     Transcript
    -0.13
    udu
    -0.13
    POSITIVE LOGITS
    /security
    0.21
     issue
    0.18
     issues
    0.18
     Issue
    0.17
     concerns
    0.17
     improvement
    0.17
    -minded
    0.16
     concern
    0.15
     minded
    0.15
    Issues
    0.15
    Act Density 0.262%

    No Known Activations