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

    Neuronpedia

    INDEX
    Explanations

    phrases related to options or choices that involve action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    consumer-related actions or advice typically involving choices and opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.89
    Cooldown
    -0.63
    SourceFile
    -0.62
     srfAttach
    -0.59
     predecessor
    -0.59
     teasp
    -0.56
     counterpart
    -0.56
     successor
    -0.54
    alian
    -0.54
    Chain
    -0.53
    POSITIVE LOGITS
     themselves
    0.94
     elect
    0.68
    selves
    0.67
     their
    0.65
    their
    0.65
     ingest
    0.65
     alike
    0.65
     THEIR
    0.64
     whom
    0.64
    ustomed
    0.61
    Act Density 1.203%

    No Known Activations