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

    Neuronpedia

    INDEX
    Explanations

    phrases describing inevitability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inevitability or certainty of outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.85
     Millennium
    -0.70
    arij
    -0.69
    ingham
    -0.67
    fil
    -0.67
    ERAL
    -0.65
    busters
    -0.64
    agra
    -0.63
    ession
    -0.63
    liter
    -0.62
    POSITIVE LOGITS
     grav
    0.84
     arises
    0.79
     dissip
    0.78
     culmin
    0.78
     arise
    0.78
     preceded
    0.76
     attracts
    0.76
    entimes
    0.75
     evolve
    0.75
     rely
    0.74
    Act Density 0.024%

    No Known Activations