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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and planning

    oai_token-act-pair · gpt-3.5-turbo

    discussions about community decisions and concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     belongs
    -0.80
    Berry
    -0.69
     Dude
    -0.69
     Stranger
    -0.66
     Digest
    -0.66
     Adolf
    -0.66
     deserves
    -0.65
     died
    -0.64
     Bene
    -0.64
     vanished
    -0.63
    POSITIVE LOGITS
     ourselves
    1.14
     anticipate
    1.01
    catentry
    0.89
     revise
    0.88
     conclude
    0.88
     allocate
    0.88
     introduce
    0.88
     foresee
    0.87
     publish
    0.87
     conclud
    0.86
    Act Density 0.725%

    No Known Activations