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

    Neuronpedia

    INDEX
    Explanations

    references to educational standards and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sond
    -0.16
     пон
    -0.15
    wij
    -0.15
    urrent
    -0.14
    utz
    -0.14
    .variant
    -0.14
     OMIT
    -0.13
    dum
    -0.13
    во
    -0.13
    волÑı
    -0.13
    POSITIVE LOGITS
     everything
    0.22
     Everything
    0.20
    Everything
    0.18
    everything
    0.18
     various
    0.16
    obot
    0.16
     certain
    0.15
     items
    0.14
    MenuStrip
    0.14
     TED
    0.14
    Act Density 0.628%

    No Known Activations