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

    Neuronpedia

    INDEX
    Explanations

    calls to action for someone to do something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the need for assistance or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Locations
    -0.78
    urations
    -0.72
    catentry
    -0.71
    ivities
    -0.70
    IVERS
    -0.68
    ischer
    -0.67
    tnc
    -0.66
     deployments
    -0.65
    itivity
    -0.65
     intrins
    -0.64
    POSITIVE LOGITS
    else
    0.95
     whom
    0.92
    who
    0.76
    acea
    0.73
    achy
    0.73
     knows
    0.72
    kn
    0.71
    afia
    0.71
    ocene
    0.70
     who
    0.67
    Act Density 0.436%

    No Known Activations