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

    Neuronpedia

    INDEX
    Explanations

    indicators of programming or computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.84
     myſelf
    -0.79
     Shakspeare
    -0.74
     Anſ
    -0.73
     Theſe
    -0.72
     preſent
    -0.72
     itſelf
    -0.69
    findpost
    -0.69
    ſelves
    -0.68
     Conſ
    -0.68
    POSITIVE LOGITS
     adds
    0.61
     acquisitions
    0.60
    Adds
    0.58
     acquired
    0.57
     adding
    0.57
    Adding
    0.56
     Adds
    0.56
    adds
    0.53
     acquiring
    0.53
     Adding
    0.52
    Act Density 0.392%

    No Known Activations