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

    Neuronpedia

    INDEX
    Explanations

    keywords related to detection and identifying anomalies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to detecting or identifying various conditions or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mort
    -0.82
    emate
    -0.75
    perty
    -0.74
    creation
    -0.73
    asin
    -0.70
    ammy
    -0.69
    adra
    -0.66
    nesia
    -0.66
    yss
    -0.65
     aven
    -0.65
    POSITIVE LOGITS
    ively
    0.84
     detect
    0.78
     flaws
    0.77
    ibles
    0.76
    ible
    0.74
    wana
    0.74
     faults
    0.72
    ministic
    0.71
     detects
    0.71
     detection
    0.70
    Act Density 0.021%

    No Known Activations