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

    Neuronpedia

    INDEX
    Explanations

    header or introductory markers indicating a beginning of a new section or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.66
     supposedly
    -0.66
    <eos>
    -0.63
     clunky
    -0.61
     desperation
    -0.59
    UI
    -0.57
     clueless
    -0.56
     A
    -0.56
     supposed
    -0.56
     exactly
    -0.55
    POSITIVE LOGITS
     itſelf
    1.24
     myſelf
    1.22
    ſelf
    1.19
     pleaſure
    1.12
    ſelves
    1.12
     auffi
    1.11
     purpoſe
    1.10
     Efq
    1.08
     ſtate
    1.05
     cauſe
    1.04
    Act Density 0.304%

    No Known Activations