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

    Neuronpedia

    INDEX
    Explanations

    text related to explaining, describing, discussing, or covering something in detail

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ief
    -0.68
    WT
    -0.68
    Hon
    -0.65
    Bridge
    -0.64
    mouth
    -0.64
    cil
    -0.64
    ñ
    -0.62
    corn
    -0.62
    achable
    -0.62
    ometers
    -0.60
    POSITIVE LOGITS
     why
    1.20
     how
    1.18
     WHY
    0.99
    why
    0.98
     some
    0.93
     aspects
    0.92
     similarities
    0.89
     examples
    0.88
     exactly
    0.86
     specifics
    0.85
    Act Density 0.197%

    No Known Activations