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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols commonly used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.31
    ING
    -0.23
    ĶåĽŀ
    -0.19
    ish
    -0.18
    496
    -0.16
    ness
    -0.15
    s
    -0.15
    ime
    -0.15
    agina
    -0.14
    chemy
    -0.14
    POSITIVE LOGITS
    'gc
    0.17
    $MESS
    0.14
    eland
    0.13
     Irvine
    0.13
    chio
    0.13
     vast
    0.13
    uler
    0.13
    ÑĪкÑĥ
    0.13
    uhl
    0.13
     Saw
    0.13
    Act Density 0.164%

    No Known Activations