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

    Neuronpedia

    INDEX
    Explanations

    album or song titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters, brands, or notable cultural elements in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.88
     admitting
    -0.66
     reporting
    -0.64
     confidential
    -0.64
    é¾įå¥ij士
    -0.63
     abst
    -0.63
     diplom
    -0.63
     proportional
    -0.62
     terms
    -0.61
     geographically
    -0.60
    POSITIVE LOGITS
    astery
    0.93
    atorium
    0.89
    agogue
    0.88
    tones
    0.86
    ixtape
    0.85
    allion
    0.82
    istries
    0.82
    apes
    0.81
    ifier
    0.80
    ograph
    0.80
    Act Density 0.521%

    No Known Activations