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

    Neuronpedia

    INDEX
    Explanations

    patterns indicating a reference to statistical data or numerical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etu
    -0.16
    -0.15
    383
    -0.15
    IRON
    -0.15
    elect
    -0.15
    oooo
    -0.14
    oooooooo
    -0.14
    CESS
    -0.14
    ooo
    -0.14
    angel
    -0.14
    POSITIVE LOGITS
    rd
    0.21
    soever
    0.20
    ãģĬãĤĬ
    0.17
    -quarters
    0.16
    ched
    0.16
    abouts
    0.16
    isha
    0.16
    alers
    0.15
    edly
    0.15
    à¸ľ
    0.15
    Act Density 0.439%

    No Known Activations