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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the act of someone or something being noticed or taken into consideration

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attention and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.72
    ambo
    -0.68
    hoe
    -0.64
    bia
    -0.63
    addon
    -0.62
     Waste
    -0.61
     cheated
    -0.61
    ili
    -0.60
     spaghetti
    -0.59
     Viet
    -0.59
    POSITIVE LOGITS
     largeDownload
    0.76
     respons
    0.75
    çİĭ
    0.75
    æ©
    0.72
     seriously
    0.71
    _-_
    0.67
    essage
    0.65
    ãĥīãĥ©
    0.64
     Canter
    0.62
     seiz
    0.62
    Act Density 0.047%

    No Known Activations