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

    Neuronpedia

    INDEX
    Explanations

    code syntax that identifies specific functions or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to social or political commentaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.74
     juggling
    -0.72
     guiActiveUnfocused
    -0.71
     scattering
    -0.71
     shack
    -0.70
     charisma
    -0.70
     fortun
    -0.67
     Suzuki
    -0.67
    è£ħ
    -0.66
     seiz
    -0.66
    POSITIVE LOGITS
    £
    1.03
    ¼
    1.01
    Ń
    0.93
    ¢
    0.93
    ¬
    0.93
    º
    0.92
    Ĵ
    0.90
    ould
    0.89
    ķ
    0.89
    ¤
    0.88
    Act Density 0.122%

    No Known Activations