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

    Neuronpedia

    INDEX
    Explanations

    occurrences or actions related to repeating or replaying something

    oai_token-act-pair · gpt-3.5-turbo

    references to sports-related replays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omo
    -0.72
    hatt
    -0.71
    iasm
    -0.70
    ymm
    -0.70
    osi
    -0.69
    kers
    -0.69
    byn
    -0.68
    essen
    -0.68
    ello
    -0.68
    ismo
    -0.67
    POSITIVE LOGITS
     replay
    1.38
     Replay
    0.74
    rog
    0.72
     repl
    0.68
    Revolution
    0.67
    Mut
    0.64
    ability
    0.64
     psychiat
    0.63
     gratification
    0.63
    able
    0.62
    Act Density 0.012%

    No Known Activations