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

    Neuronpedia

    INDEX
    Explanations

    references to town hall meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to town hall events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Raf
    -0.69
    itars
    -0.69
    ossibility
    -0.68
    ihad
    -0.67
     Torres
    -0.66
    unct
    -0.65
    raints
    -0.64
     NYT
    -0.63
    ression
    -0.63
    asive
    -0.63
    POSITIVE LOGITS
     hall
    1.26
     halls
    1.06
    hall
    0.91
    iday
    0.86
    ways
    0.82
    aday
    0.82
    marks
    0.81
    Hall
    0.79
    naires
    0.78
    halla
    0.77
    Act Density 0.008%

    No Known Activations