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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    иÑĤелÑĮноÑģÑĤÑĮ
    -0.15
    rescia
    -0.14
    Č↵
    -0.13
    ayo
    -0.13
    uru
    -0.13
    usch
    -0.13
    =yes
    -0.13
    ادگÛĮ
    -0.12
    ãĥŃãĥ¼
    -0.12
    ãĥĥãĥĦ
    -0.12
    POSITIVE LOGITS
     heck
    0.26
     hell
    0.26
     step
    0.23
    hell
    0.20
     notch
    0.20
     that
    0.20
    heck
    0.20
     Hell
    0.19
     those
    0.19
     you
    0.19
    Act Density 0.038%

    No Known Activations