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

    Neuronpedia

    INDEX
    Explanations

    websites and web addresses

    oai_token-act-pair · gpt-3.5-turbo

    web addresses or domains related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :]
    -0.63
     indign
    -0.58
    ensibly
    -0.58
     ridiculed
    -0.56
    Īè
    -0.56
     disparate
    -0.55
     fuss
    -0.55
     mass
    -0.54
     mirac
    -0.54
     clashed
    -0.54
    POSITIVE LOGITS
    /.
    1.49
    /,
    1.30
    /#
    1.08
     Alternatively
    1.08
    /?
    1.08
     .
    1.00
     Follow
    0.98
    <|endoftext|>
    0.91
    /+
    0.90
    /)
    0.90
    Act Density 0.099%

    No Known Activations