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

    Neuronpedia

    INDEX
    Explanations

    sections or elements related to statistical or experimental data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    able
    -0.58
    Bibliograf
    -0.58
    ings
    -0.55
    -0.54
    ing
    -0.51
    ING
    -0.49
    ize
    -0.49
    ofthe
    -0.48
    ized
    -0.48
    followed
    -0.48
    POSITIVE LOGITS
    umenti
    0.60
     CWE
    0.59
    umenta
    0.58
    regated
    0.58
    ressions
    0.56
    umenter
    0.54
    ruitment
    0.53
    ulously
    0.51
    ‍♂️
    0.50
    umented
    0.49
    Act Density 0.783%

    No Known Activations