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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лиÑĤ
    -0.15
    _usb
    -0.14
    vect
    -0.14
    /misc
    -0.14
    ÑĥÑģа
    -0.14
    rawer
    -0.13
    uš
    -0.13
    Printf
    -0.13
    .TAG
    -0.13
    gel
    -0.13
    POSITIVE LOGITS
     appearing
    0.86
     appeared
    0.86
     appearance
    0.85
     appear
    0.84
     appearances
    0.79
     appears
    0.77
     Appearance
    0.74
    appear
    0.73
     apare
    0.72
     Appears
    0.69
    Act Density 0.066%

    No Known Activations