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

    Neuronpedia

    INDEX
    Explanations

    words that imply a negative or dishonorable action or attribute

    oai_token-act-pair · gpt-4-turbo

    words related to dishonesty or dishonorable behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to dishonesty and honorable actions, including high-stakes situations and individuals associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esta
    -0.95
    agy
    -0.82
    isine
    -0.81
    izens
    -0.80
    urgy
    -0.80
    rooms
    -0.76
    heast
    -0.74
    ele
    -0.74
    arian
    -0.73
    icles
    -0.72
    POSITIVE LOGITS
    RECT
    0.79
    CLAIM
    0.77
    é»Ĵ
    0.75
    POSE
    0.75
    BuyableInstoreAndOnline
    0.75
    åĬ
    0.71
    ments
    0.70
     omission
    0.69
    \\\\\\\\\\\\\\\\
    0.69
    OUP
    0.67
    Act Density 0.033%

    No Known Activations