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

    Neuronpedia

    INDEX
    Explanations

    special characters signaling emphasis or action in text

    oai_token-act-pair · gpt-3.5-turbo

    a specific unknown character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.76
     Libyan
    -0.68
     Droid
    -0.67
     guiActiveUnfocused
    -0.66
     lodging
    -0.66
     Moroccan
    -0.65
     CLR
    -0.64
     radius
    -0.62
     Drawn
    -0.62
     DPR
    -0.62
    POSITIVE LOGITS
    ¹
    1.09
    º
    1.03
    agree
    0.96
    £
    0.94
    Į
    0.90
    Ĵ
    0.89
    ¢
    0.89
    ¬
    0.88
    ¿
    0.88
    ı
    0.88
    Act Density 0.246%

    No Known Activations