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

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords related to technology and data

    oai_token-act-pair · gpt-3.5-turbo

    significant comparisons or contrasts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leader
    -0.75
    hement
    -0.70
     nails
    -0.68
    atile
    -0.66
    ivably
    -0.63
    xual
    -0.62
     OU
    -0.61
     Instr
    -0.61
     Lung
    -0.60
     LI
    -0.59
    POSITIVE LOGITS
    hello
    1.02
    ccording
    0.95
    Overview
    0.87
    ³³³³³³³³³³³³³³³³
    0.85
    Posted
    0.81
    ¶
    0.80
    science
    0.77
    Firstly
    0.77
    resistant
    0.76
    Reading
    0.76
    Act Density 0.245%

    No Known Activations