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

    Neuronpedia

    INDEX
    Explanations

    programming syntax related sequences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    comings
    -0.82
    landish
    -0.78
    oven
    -0.77
    Utah
    -0.75
    agonists
    -0.74
    offensive
    -0.74
    anski
    -0.73
    Reloaded
    -0.72
    anthrop
    -0.72
    Tube
    -0.71
    POSITIVE LOGITS
     if
    1.20
     return
    1.12
     println
    1.09
     else
    1.06
     printf
    1.05
     Console
    1.02
     var
    1.00
     /*
    0.99
     }
    0.99
     //
    0.97
    Act Density 0.060%

    No Known Activations