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

    Neuronpedia

    INDEX
    Explanations

    comparative words and phrases, such as "more than," "higher than," "less," "better," and "limited."

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases reflecting improvements or changes in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folios
    -0.77
    bryce
    -0.71
     Ellison
    -0.71
    ë
    -0.66
    Wiki
    -0.64
     Bucc
    -0.62
    afa
    -0.60
    minster
    -0.59
    opa
    -0.57
    doms
    -0.57
    POSITIVE LOGITS
     nonetheless
    0.82
     importantly
    0.75
    etheless
    0.69
    cknowled
    0.64
     alike
    0.64
    .<
    0.62
    !--
    0.62
     anyway
    0.62
    cffffcc
    0.62
     thereafter
    0.59
    Act Density 0.799%

    No Known Activations