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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical theories and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iting
    -0.17
    ited
    -0.15
    cing
    -0.14
    ability
    -0.14
     McKay
    -0.14
    urs
    -0.14
    isure
    -0.14
    lifetime
    -0.13
    volt
    -0.13
    .nl
    -0.13
    POSITIVE LOGITS
    esson
    0.15
    бÑĥдÑĮ
    0.14
    $LANG
    0.14
     详æĥħ
    0.14
    aines
    0.14
     Owners
    0.13
    $MESS
    0.13
    rien
    0.13
    ampire
    0.13
     caz
    0.13
    Act Density 0.037%

    No Known Activations