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

    Neuronpedia

    INDEX
    Explanations

    words related to uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iya
    -0.80
    elight
    -0.76
    iates
    -0.74
    issy
    -0.72
    uctor
    -0.70
    lette
    -0.70
    ife
    -0.69
    iate
    -0.69
    ible
    -0.69
    Materials
    -0.69
    POSITIVE LOGITS
     misunder
    0.83
     underestimate
    0.76
     someday
    0.75
     underest
    0.71
     subconscious
    0.69
     overest
    0.68
     forgot
    0.68
     owe
    0.68
     quir
    0.68
     won
    0.66
    Act Density 0.048%

    No Known Activations