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

    Neuronpedia

    INDEX
    Explanations

    verbs related to revealing or bringing to light something previously hidden or unknown

    oai_token-act-pair · gpt-3.5-turbo

    terms related to revealing or disclosing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.69
    tesy
    -0.68
    ricting
    -0.67
    erent
    -0.66
    colo
    -0.64
     Lumpur
    -0.64
    aque
    -0.64
    illard
    -0.63
    rior
    -0.63
    wise
    -0.62
    POSITIVE LOGITS
     Breach
    0.89
     exposing
    0.87
    Versions
    0.87
    ibilities
    0.80
     exposed
    0.78
    é¾
    0.77
    IBLE
    0.77
     Exposure
    0.77
    м
    0.76
    çīĪ
    0.73
    Act Density 0.015%

    No Known Activations