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

    Neuronpedia

    INDEX
    Explanations

    the word "well" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ee
    -0.15
    yen
    -0.15
     flash
    -0.15
    ouflage
    -0.14
    at
    -0.14
    yms
    -0.14
    843
    -0.14
    aida
    -0.14
    ofile
    -0.14
    atown
    -0.14
    POSITIVE LOGITS
    ington
    0.23
    spring
    0.21
    -known
    0.20
    nesday
    0.19
    ows
    0.18
    fare
    0.17
    come
    0.17
    -being
    0.16
     enough
    0.16
    NES
    0.15
    Act Density 0.044%

    No Known Activations