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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contrasting and comparing different entities

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to biology and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspended
    -0.59
     Logo
    -0.57
     Rouge
    -0.57
    ban
    -0.57
     NPCs
    -0.56
     Poster
    -0.55
     ducks
    -0.54
     chill
    -0.54
     conveniently
    -0.54
     Converted
    -0.53
    POSITIVE LOGITS
     respects
    1.03
     regard
    0.92
    ahime
    0.92
     matters
    0.90
     regards
    0.89
     direction
    0.87
     estimation
    0.85
     terms
    0.82
     metrics
    0.80
     rankings
    0.80
    Act Density 0.372%

    No Known Activations