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

    Neuronpedia

    INDEX
    Explanations

    structured numeric patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.84
    iqueness
    -0.67
    umenthal
    -0.66
    ESA
    -0.66
     Kepler
    -0.66
    blance
    -0.64
    esa
    -0.64
     filibuster
    -0.64
    uously
    -0.63
     tremend
    -0.63
    POSITIVE LOGITS
    teenth
    0.75
    USD
    0.68
    thur
    0.67
     ABV
    0.67
    390
    0.66
    ãĥ´ãĤ¡
    0.66
     cones
    0.66
    72
    0.66
    421
    0.65
    otom
    0.65
    Act Density 0.167%

    No Known Activations