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

    Neuronpedia

    INDEX
    Explanations

    references to terminals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    748
    -0.16
    pu
    -0.16
    ëª
    -0.16
    ordinate
    -0.15
    ed
    -0.15
    ness
    -0.15
    rub
    -0.14
    ey
    -0.14
    ively
    -0.14
    ord
    -0.14
    POSITIVE LOGITS
    inals
    0.20
    perature
    0.16
    /start
    0.15
     Gravity
    0.15
    à¥įपर
    0.15
    isay
    0.15
     gravity
    0.14
    adata
    0.14
    Gravity
    0.14
     Ter
    0.14
    Act Density 0.024%

    No Known Activations