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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions in a technical context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ously
    -0.67
    .):
    -0.64
    zbek
    -0.64
    osition
    -0.63
    pell
    -0.63
    pace
    -0.61
    ost
    -0.58
    orts
    -0.57
    lete
    -0.57
    olute
    -0.56
    POSITIVE LOGITS
    _-
    1.60
    =-=-=-=-=-=-=-=-
    1.18
    =-=-=-=-
    1.11
    webkit
    1.03
    /-
    1.02
    =-=-
    0.95
    \-
    0.92
    sama
    0.89
    SIGN
    0.85
    taboola
    0.82
    Act Density 0.731%

    No Known Activations