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

    Neuronpedia

    INDEX
    Explanations

    websites and online platforms

    oai_token-act-pair · gpt-3.5-turbo

    web addresses and domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensibly
    -0.67
     Barkley
    -0.65
    Īè
    -0.64
     Myst
    -0.56
    pires
    -0.54
    Marginal
    -0.54
    Balt
    -0.54
     Monk
    -0.53
     metic
    -0.52
     disparate
    -0.52
    POSITIVE LOGITS
    /.
    1.29
    /,
    1.14
    /?
    1.08
     Alternatively
    1.05
    <|endoftext|>
    1.03
    /#
    1.00
     .
    0.92
     ).
    0.92
     Follow
    0.89
    *.
    0.86
    Act Density 0.109%

    No Known Activations