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

    Neuronpedia

    INDEX
    Explanations

    medical and health-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reloaded
    -0.74
    coni
    -0.72
     Helpful
    -0.70
     Hundred
    -0.69
     Duo
    -0.68
     Rouge
    -0.67
     Albion
    -0.66
    rers
    -0.65
     Argon
    -0.65
     Delta
    -0.65
    POSITIVE LOGITS
    span
    1.19
    iest
    1.18
     care
    1.10
    care
    1.10
    ful
    1.06
    ily
    1.01
    fulness
    0.96
     insurance
    0.95
     hazards
    0.95
     detrim
    0.93
    Act Density 0.043%

    No Known Activations