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

    Neuronpedia

    INDEX
    Explanations

    references to changes or transitions between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with music and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.52
    onto
    -0.51
     helicop
    -0.50
    Instead
    -0.48
    STEP
    -0.48
     withdraw
    -0.47
     THEN
    -0.47
     withdrew
    -0.47
    arettes
    -0.46
    arations
    -0.46
    POSITIVE LOGITS
     fascination
    0.70
    pmwiki
    0.70
     fascinated
    0.66
     often
    0.65
     rumours
    0.63
    catentry
    0.63
     understandably
    0.63
     misconception
    0.62
     lately
    0.62
     misconceptions
    0.62
    Act Density 1.055%

    No Known Activations