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

    Neuronpedia

    INDEX
    Explanations

    information related to real-life events and experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to real-life situations and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pigs
    -0.63
     Welch
    -0.61
     REM
    -0.61
     Alleg
    -0.60
    cknowled
    -0.59
    enced
    -0.57
    REM
    -0.56
    BL
    -0.56
     Quit
    -0.55
     Zimmer
    -0.55
    POSITIVE LOGITS
    eers
    0.82
    âĶĢâĶĢâĶĢâĶĢ
    0.78
    upid
    0.73
    oppable
    0.73
    gypt
    0.70
    advertising
    0.70
    rencies
    0.68
    liness
    0.68
    atoes
    0.67
    ragon
    0.67
    Act Density 0.085%

    No Known Activations