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

    Neuronpedia

    INDEX
    Explanations

    abbreviations, acronyms, or shorthand representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hide
    -0.18
    à¥įड
    -0.17
    rq
    -0.16
    richt
    -0.15
    host
    -0.15
    ãģĦãĤĭ
    -0.15
    had
    -0.15
    led
    -0.15
    hol
    -0.15
    har
    -0.14
    POSITIVE LOGITS
    ted
    0.19
    repid
    0.18
    tings
    0.18
    tal
    0.18
    ãģĬãĤĬ
    0.18
    imestep
    0.17
    ropolis
    0.17
    uesday
    0.17
    umblr
    0.17
    tems
    0.17
    Act Density 0.172%

    No Known Activations