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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rency
    -0.75
    ciating
    -0.71
    icial
    -0.65
    efeated
    -0.64
    feeding
    -0.64
     Everywhere
    -0.63
     Fighter
    -0.61
    olis
    -0.59
     Kush
    -0.59
    izabeth
    -0.58
    POSITIVE LOGITS
    haps
    1.23
    hap
    1.20
    onna
    1.18
    bes
    1.07
     be
    0.99
     someday
    0.83
     differ
    0.82
     owe
    0.81
    flies
    0.81
     derive
    0.80
    Act Density 0.074%

    No Known Activations