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

    Neuronpedia

    INDEX
    Explanations

    references to voting and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.48
     themſelves
    -1.35
     itſelf
    -1.32
     himſelf
    -1.31
     houſe
    -1.29
     purpoſe
    -1.26
     myſelf
    -1.24
     becauſe
    -1.24
     reaſon
    -1.23
     ſhe
    -1.22
    POSITIVE LOGITS
     album
    0.60
     L
    0.59
     Far
    0.58
     Fra
    0.58
     Un
    0.57
     (
    0.56
     
    0.55
    <eos>
    0.55
     M
    0.55
    ↵
    0.55
    Act Density 0.144%

    No Known Activations