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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong positive sentiment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong affection or enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pter
    -0.69
     regretted
    -0.69
     suffice
    -0.68
    laim
    -0.67
     reluct
    -0.66
    authorized
    -0.66
    uthor
    -0.64
    ailable
    -0.64
     dilig
    -0.63
    ident
    -0.61
    POSITIVE LOGITS
     gravy
    0.66
     idea
    0.66
    animous
    0.64
    housing
    0.60
     decoration
    0.59
     NCT
    0.58
     Flip
    0.58
     simplicity
    0.57
     symmetry
    0.57
     guts
    0.56
    Act Density 0.174%

    No Known Activations