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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.94
    mes
    -0.76
    Contents
    -0.62
     captcha
    -0.62
    uga
    -0.60
     wed
    -0.59
    luaj
    -0.57
    Īè
    -0.56
    scribed
    -0.56
     dismantled
    -0.56
    POSITIVE LOGITS
     confidently
    1.11
     anecd
    0.85
     definitively
    0.79
     unequivocally
    0.71
    quist
    0.67
     firsthand
    0.67
     safely
    0.67
     Comfort
    0.66
     comfortably
    0.66
    frog
    0.65
    Act Density 0.095%

    No Known Activations