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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clarity and certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating clarity and simplicity in descriptions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-
    -0.78
    iannopoulos
    -0.73
    URA
    -0.72
    shi
    -0.72
    è¦ļéĨĴ
    -0.71
    trak
    -0.71
    abilia
    -0.70
    =-=-=-=-=-=-=-=-
    -0.70
    anova
    -0.68
    Tx
    -0.66
    POSITIVE LOGITS
     Present
    0.72
     Bernstein
    0.72
    iquette
    0.69
     borders
    0.67
     transparent
    0.66
     prism
    0.65
     concise
    0.65
    perse
    0.65
    ©¶æ
    0.64
    cise
    0.64
    Act Density 0.408%

    No Known Activations