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

    Neuronpedia

    INDEX
    Explanations

    Keywords related to academic and organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hand
    -0.23
    hol
    -0.21
    hide
    -0.21
    hattan
    -0.19
    erb
    -0.18
    hart
    -0.18
    haft
    -0.18
    hood
    -0.18
    hit
    -0.18
    half
    -0.18
    POSITIVE LOGITS
    ting
    0.37
    ãģĬãĤĬ
    0.26
    ted
    0.25
    imestep
    0.23
    tings
    0.23
    esseract
    0.23
    iffany
    0.23
    ters
    0.23
    umblr
    0.22
    aylor
    0.22
    Act Density 2.638%

    No Known Activations