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

    Neuronpedia

    INDEX
    Explanations

    phrases related to asserting or claiming something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert claims or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stice
    -0.70
    ersen
    -0.67
    rade
    -0.66
    arry
    -0.66
    hens
    -0.65
    oyer
    -0.65
    course
    -0.65
    mitt
    -0.64
    urch
    -0.60
    itcher
    -0.60
    POSITIVE LOGITS
     innocence
    0.91
    Downloadha
    0.90
     deduction
    0.79
     authenticity
    0.77
    ĪĴ
    0.77
    ãĥ´
    0.77
    ¥µ
    0.72
    ©¶æ
    0.72
     justification
    0.72
     superiority
    0.72
    Act Density 0.147%

    No Known Activations