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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to unspecified individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to an undefined or generic 'someone'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.79
    osterone
    -0.78
    heny
    -0.74
    inders
    -0.68
    interest
    -0.68
    enegger
    -0.66
    èª
    -0.66
    ory
    -0.65
    irth
    -0.65
    ortex
    -0.63
    POSITIVE LOGITS
     else
    1.60
    Else
    1.28
     Else
    1.00
    else
    0.95
    WithNo
    0.89
    ĪĴ
    0.75
     who
    0.74
     smugg
    0.73
    rency
    0.71
     clicked
    0.70
    Act Density 0.036%

    No Known Activations