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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "This."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ous
    -0.16
    ish
    -0.15
    ed
    -0.15
    ille
    -0.15
    ive
    -0.15
    fos
    -0.15
    mans
    -0.14
    iye
    -0.14
    ahl
    -0.14
     Passed
    -0.14
    POSITIVE LOGITS
    oretical
    0.18
    ãĥ£
    0.18
    DisplayStyle
    0.17
    êu
    0.16
    CLUDING
    0.16
    oret
    0.15
    pite
    0.15
    odka
    0.15
    557
    0.14
    ван
    0.14
    Act Density 0.125%

    No Known Activations