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

    Neuronpedia

    INDEX
    Explanations

    editing-related terms and version updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amar
    -0.15
    ile
    -0.15
    ancer
    -0.15
     gall
    -0.14
    ber
    -0.14
    pte
    -0.14
    ,False
    -0.13
     Jeho
    -0.13
    	Copyright
    -0.13
    amoto
    -0.13
    POSITIVE LOGITS
    :
    0.23
    rens
    0.15
    ा:
    0.15
    ohl
    0.14
    ály
    0.13
    ád
    0.13
    اÙģت
    0.13
    edl
    0.13
    drm
    0.13
    dbe
    0.13
    Act Density 0.069%

    No Known Activations