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

    Neuronpedia

    INDEX
    Explanations

    commands and codes commonly used in computer programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    liest
    -0.97
    nery
    -0.92
    umin
    -0.91
    raits
    -0.90
    ieth
    -0.90
    wan
    -0.88
    vae
    -0.88
     Icelandic
    -0.88
     Arabian
    -0.85
     Pwr
    -0.85
    POSITIVE LOGITS
    PLIC
    1.25
    BAT
    1.24
    plet
    1.05
    MENT
    0.98
    AX
    0.98
    ply
    0.96
    ABLE
    0.95
    PLIED
    0.94
    EMENT
    0.94
    fortable
    0.94
    Act Density 0.116%

    No Known Activations