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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sequence or order

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ordinal numbers and their significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.74
    atan
    -0.71
    iw
    -0.71
    wi
    -0.67
    pload
    -0.66
    dot
    -0.65
    nick
    -0.64
     Zi
    -0.63
    ITH
    -0.63
    yahoo
    -0.63
    POSITIVE LOGITS
     onwards
    0.71
     onward
    0.68
     Centauri
    0.64
     Anniversary
    0.63
     Dragonbound
    0.63
     Skydragon
    0.61
    ħĭ
    0.60
     finale
    0.59
    milo
    0.59
     Premiere
    0.58
    Act Density 0.049%

    No Known Activations