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

    Neuronpedia

    INDEX
    Explanations

    elements related to figures and diagrams in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anger
    -0.16
    ltr
    -0.15
    agar
    -0.15
     Fleet
    -0.14
    acer
    -0.14
    ï¼ĭ
    -0.14
    uis
    -0.13
    italic
    -0.13
    Ñĥй
    -0.13
    uin
    -0.13
    POSITIVE LOGITS
    include
    0.24
    -caption
    0.20
     include
    0.18
     includ
    0.18
    caption
    0.18
     inclusion
    0.17
     caption
    0.17
    hs
    0.17
    resize
    0.16
    vik
    0.16
    Act Density 0.023%

    No Known Activations