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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing quality or doing things correctly

    oai_token-act-pair · gpt-3.5-turbo

    references to high quality and exceptional standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amera
    -0.74
     briefly
    -0.68
    wen
    -0.68
     unsuccessfully
    -0.67
    SPONSORED
    -0.66
     abruptly
    -0.66
    arry
    -0.66
    >:
    -0.65
    mania
    -0.64
     reportedly
    -0.63
    POSITIVE LOGITS
     best
    1.37
     utmost
    1.29
     smartest
    1.26
     fullest
    1.20
     brightest
    1.19
     widest
    1.19
     greatest
    1.18
     safest
    1.18
     basics
    1.16
     finest
    1.15
    Act Density 0.288%

    No Known Activations