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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases indicating a need for action or change

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to obligation and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlucky
    -0.67
    ãĤ¼
    -0.67
     guesses
    -0.67
     depends
    -0.65
     suggestive
    -0.65
    anticipated
    -0.65
     anticipation
    -0.65
    anka
    -0.63
     projections
    -0.62
    advant
    -0.62
    POSITIVE LOGITS
     apologize
    1.25
     cease
    1.24
     apologise
    1.23
     resign
    1.23
     stop
    1.16
     STOP
    1.15
     quit
    1.13
     rethink
    1.12
     reconsider
    1.09
     retract
    1.01
    Act Density 0.228%

    No Known Activations