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

    Neuronpedia

    INDEX
    Explanations

    short phrases or statements that have a high impact or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aper
    -0.74
     conver
    -0.71
     reformed
    -0.69
     assigned
    -0.69
     intruder
    -0.67
     orderly
    -0.67
     allied
    -0.66
     starved
    -0.64
     breeze
    -0.63
     subdued
    -0.63
    POSITIVE LOGITS
    Exit
    0.82
    [/
    0.79
    Whe
    0.74
     âĢķ
    0.72
     Lastly
    0.71
     Alas
    0.69
     Adds
    0.69
    <|endoftext|>
    0.67
     Approximately
    0.66
    Billy
    0.66
    Act Density 0.089%

    No Known Activations