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

    Neuronpedia

    INDEX
    Explanations

    technical terms and quantitative data related to processes and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     you
    -0.80
     
    -0.65
     go
    -0.65
     talking
    -0.63
     t
    -0.62
     I
    -0.62
     right
    -0.59
     baby
    -0.59
     tell
    -0.59
     goes
    -0.58
    POSITIVE LOGITS
     feroit
    0.96
     ainfi
    0.95
     auroit
    0.94
     fufficient
    0.93
     auffi
    0.91
     Monfieur
    0.91
     reaſon
    0.88
    ſelf
    0.85
     eenige
    0.85
     vettoriale
    0.85
    Act Density 3.401%

    No Known Activations