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

    Neuronpedia

    INDEX
    Explanations

    words related to replicas or reenactments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duplicates or reproductions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kers
    -0.78
    gap
    -0.70
    ymm
    -0.69
    nut
    -0.68
    iasm
    -0.67
    bara
    -0.66
    gling
    -0.66
    apa
    -0.65
    doms
    -0.64
    stop
    -0.64
    POSITIVE LOGITS
     replay
    0.90
    ays
    0.78
     reuse
    0.69
    Reviewed
    0.65
     repl
    0.64
    uel
    0.64
     Odyssey
    0.63
    ãĤ©
    0.63
    acers
    0.63
    igators
    0.62
    Act Density 0.061%

    No Known Activations