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

    Neuronpedia

    INDEX
    Explanations

    instances of contrast or exception in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    A
    -0.14
    hell
    -0.14
     foam
    -0.14
    ison
    -0.14
    TS
    -0.13
    alley
    -0.13
     Lair
    -0.13
    ãģĿãģĨãģª
    -0.13
    inue
    -0.13
    atoire
    -0.13
    POSITIVE LOGITS
    ardy
    0.17
     Blasio
    0.17
     calend
    0.17
    pty
    0.15
    edException
    0.15
    нед
    0.15
    unga
    0.15
    estone
    0.14
    -addons
    0.14
    addir
    0.14
    Act Density 0.149%

    No Known Activations