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

    Neuronpedia

    INDEX
    Explanations

    words related to symbolism and representation

    oai_token-act-pair · gpt-3.5-turbo

    words related to symbols and their representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    band
    -0.65
     upkeep
    -0.65
     voluntarily
    -0.64
    olicy
    -0.64
     boarding
    -0.64
     err
    -0.61
     unrestricted
    -0.61
     tuition
    -0.61
     uninsured
    -0.60
    ategory
    -0.60
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    0.75
    rium
    0.71
     glimps
    0.70
     parallels
    0.68
    gado
    0.64
    rities
    0.63
    atari
    0.63
     gems
    0.62
     imag
    0.62
    ordial
    0.61
    Act Density 0.230%

    No Known Activations