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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics or statistical data points, particularly percentages and rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.19
    à¹īว
    -0.16
    /libs
    -0.15
    sburgh
    -0.15
    ÑįÑĤомÑĥ
    -0.15
    agnostic
    -0.15
    ระ
    -0.15
    pear
    -0.14
    atomy
    -0.14
    ISTIC
    -0.14
    POSITIVE LOGITS
    iles
    0.18
    -plus
    0.17
    ile
    0.16
    ↵
    0.16
    aires
    0.16
     (%)
    0.15
    ivals
    0.14
    imeters
    0.14
    ropolis
    0.14
    i
    0.14
    Act Density 0.022%

    No Known Activations