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

    Neuronpedia

    INDEX
    Explanations

    programming code lines containing specific keywords like "Path", "error", "mesh", and "function"

    oai_token-act-pair · gpt-3.5-turbo

    programming-related terminology and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ancest
    -0.83
    /)
    -0.75
     acron
    -0.70
     Schne
    -0.67
    ?),
    -0.65
    ],"
    -0.65
     AMA
    -0.64
     rog
    -0.64
     paran
    -0.63
    %),
    -0.63
    POSITIVE LOGITS
     +=
    1.76
     :=
    1.46
     -=
    1.43
    ++;
    1.35
     =
    1.31
    ();
    1.16
    =(
    1.02
    +=
    1.02
     ();
    1.00
    =$
    0.95
    Act Density 0.087%

    No Known Activations