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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and structures in programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.98
     itſelf
    -1.96
     myſelf
    -1.91
     Monfieur
    -1.84
     raiſ
    -1.72
     himſelf
    -1.68
     themſelves
    -1.67
     becauſe
    -1.67
     houſe
    -1.66
     Theſe
    -1.64
    POSITIVE LOGITS
     
    0.89
    .
    0.81
     I
    0.73
     a
    0.71
     in
    0.69
     <
    0.68
    ,
    0.68
    -
    0.67
     the
    0.66
    <eos>
    0.65
    Act Density 0.262%

    No Known Activations