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

    Neuronpedia

    INDEX
    Explanations

    terms related to unauthorized actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to unauthorized activities or access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.95
    utra
    -0.78
    ills
    -0.78
    =-=-=-=-
    -0.77
    qt
    -0.77
    acea
    -0.77
    rams
    -0.76
    oleon
    -0.75
    ingham
    -0.73
    mates
    -0.72
    POSITIVE LOGITS
     disclosures
    0.89
     disclosure
    0.81
     unauthorized
    0.80
     reuse
    0.76
     intruder
    0.75
     access
    0.74
    WARE
    0.74
     permission
    0.72
    aneous
    0.70
     downloads
    0.69
    Act Density 0.020%

    No Known Activations