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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a range

    oai_token-act-pair · gpt-3.5-turbo

    references to sources or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faced
    -0.74
    resy
    -0.74
    sic
    -0.74
    SPONSORED
    -0.72
    git
    -0.70
    win
    -0.69
    isode
    -0.68
    ense
    -0.68
    é¾įåĸļ士
    -0.68
    tell
    -0.65
    POSITIVE LOGITS
     afar
    0.92
     lowly
    0.76
     humble
    0.76
     mild
    0.73
     toddlers
    0.71
     beginner
    0.71
     mildly
    0.69
     weddings
    0.69
     mundane
    0.69
     infancy
    0.68
    Act Density 0.074%

    No Known Activations