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

    Neuronpedia

    INDEX
    Explanations

    words related to numerical quantities and measurements

    oai_token-act-pair · gpt-3.5-turbo

    instances of numbers and quantitative measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grateful
    -0.59
     Wolfe
    -0.55
     Rivera
    -0.54
     Franks
    -0.53
     Ange
    -0.53
     Schr
    -0.52
     Floyd
    -0.51
     Walters
    -0.51
     Ruby
    -0.50
     Pokémon
    -0.50
    POSITIVE LOGITS
    trak
    0.85
    oother
    0.76
    qus
    0.73
    arser
    0.71
     versa
    0.69
    iliate
    0.68
     theirs
    0.68
    ocre
    0.68
     thereto
    0.68
    anooga
    0.66
    Act Density 1.512%

    No Known Activations