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

    Neuronpedia

    INDEX
    Explanations

    newspaper names

    oai_token-act-pair · gpt-3.5-turbo

    references to news publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.76
     "$:/
    -0.68
    stood
    -0.65
     silence
    -0.64
     beds
    -0.64
     bushes
    -0.62
     rounds
    -0.59
     check
    -0.59
    =>
    -0.59
    itatively
    -0.59
    POSITIVE LOGITS
    utterstock
    1.35
    imedia
    0.91
     Images
    0.89
    alyst
    0.86
    intendent
    0.82
    ynam
    0.79
     Shutterstock
    0.77
    ĺħ
    0.74
     Photo
    0.73
    NBC
    0.73
    Act Density 0.069%

    No Known Activations