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

    Neuronpedia

    INDEX
    Explanations

    content related to plans and future intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unca
    -0.17
    lico
    -0.16
     ever
    -0.14
    以æĿ¥
    -0.14
    acific
    -0.14
     never
    -0.14
    ÑģпÑĸлÑĮ
    -0.14
    ominated
    -0.13
     rarely
    -0.13
    ronic
    -0.13
    POSITIVE LOGITS
     currently
    0.62
     presently
    0.58
    currently
    0.55
     Currently
    0.54
    Currently
    0.52
    缮åīį
    0.45
     пока
    0.43
     until
    0.39
     current
    0.38
    æļĤ
    0.37
    Act Density 0.294%

    No Known Activations