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

    Neuronpedia

    INDEX
    Explanations

    terms related to progressing or improving something further

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skipping
    -0.67
    Reviewer
    -0.66
     Going
    -0.64
     LOT
    -0.64
     Tsukuyomi
    -0.64
     happening
    -0.64
     boarding
    -0.63
     quitting
    -0.63
     Walking
    -0.63
     sitting
    -0.63
    POSITIVE LOGITS
     differentiate
    1.25
     enhance
    1.23
     regulate
    1.19
     stimulate
    1.18
     integrate
    1.17
     complicate
    1.16
     define
    1.15
     promote
    1.15
     characterize
    1.14
     resemble
    1.12
    Act Density 0.097%

    No Known Activations