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

    Neuronpedia

    INDEX
    Explanations

    sequences of dashes and similar characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     „
    -1.14
    „
    -0.88
    ••••
    -0.78
     «
    -0.78
    «
    -0.74
    ◯
    -0.73
     („
    -0.72
    OwnProperty
    -0.69
    ⟨
    -0.69
    ————————
    -0.67
    POSITIVE LOGITS
     --
    2.00
    --
    1.88
    '--
    1.88
    ,--
    1.86
    .--
    1.82
    "--
    1.81
    !--
    1.71
    //--
    1.69
     '--
    1.66
    --"
    1.64
    Act Density 0.396%

    No Known Activations