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

    Neuronpedia

    INDEX
    Explanations

    words related to significant or impressive events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rises, appearances, or credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lift
    -0.73
    yne
    -0.65
     screening
    -0.65
     Beautiful
    -0.65
     Passenger
    -0.62
     Murd
    -0.60
    pedia
    -0.60
     withholding
    -0.59
     Traff
    -0.58
     scanning
    -0.56
    POSITIVE LOGITS
    oths
    0.88
    ptions
    0.85
    ours
    0.82
    cture
    0.79
    warts
    0.78
    estone
    0.77
    estones
    0.77
    yssey
    0.76
    iances
    0.75
    eties
    0.75
    Act Density 0.122%

    No Known Activations