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

    Neuronpedia

    INDEX
    Explanations

    keywords related to configurations and parameters in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.73
     
    -0.72
    <eos>
    -0.72
    -
    -0.63
     (
    -0.61
     in
    -0.60
     for
    -0.60
     -
    -0.59
    (
    -0.59
    ;
    -0.59
    POSITIVE LOGITS
     Efq
    1.83
     myſelf
    1.62
     Majefty
    1.51
     Jefus
    1.49
     themſelves
    1.49
     itſelf
    1.49
     Monfieur
    1.44
     ſeveral
    1.44
    ſelf
    1.44
     houſe
    1.41
    Act Density 0.116%

    No Known Activations