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

    Neuronpedia

    INDEX
    Explanations

    code snippets enclosed in backticks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    •••
    -0.85
    ••••
    -0.81
     neb
    -0.77
     Paredes
    -0.77
    avajillas
    -0.74
    er
    -0.73
     Penh
    -0.72
     Norwood
    -0.71
     oub
    -0.71
    —"
    -0.71
    POSITIVE LOGITS
     `
    1.87
    .`
    1.83
    =`
    1.83
    :`
    1.76
    {`
    1.68
     (`
    1.65
    >`
    1.63
    )`
    1.62
    (`
    1.60
     `<
    1.55
    Act Density 0.079%

    No Known Activations