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

    Neuronpedia

    INDEX
    Explanations

    numeric or alphanumeric codes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     tert
    -0.78
     tremend
    -0.73
     sender
    -0.73
     seiz
    -0.72
    ADRA
    -0.70
     accomp
    -0.68
     flare
    -0.66
     occas
    -0.66
    ctions
    -0.65
     rall
    -0.65
    POSITIVE LOGITS
    ings
    1.13
    stone
    1.08
    bread
    1.06
    bones
    1.02
    ingly
    1.01
    bridge
    1.00
    sheets
    0.99
    stakes
    0.99
    grass
    0.98
    hound
    0.96
    Act Density 0.250%

    No Known Activations