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

    Neuronpedia

    INDEX
    Explanations

    negative or restrictive phrases, particularly using the word "nor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sel
    -0.17
    ano
    -0.16
    anim
    -0.15
    enko
    -0.14
     Franken
    -0.14
    ing
    -0.14
    392
    -0.14
     niet
    -0.13
    NotNull
    -0.13
    urs
    -0.13
    POSITIVE LOGITS
    lify
    0.17
    deen
    0.16
     any
    0.16
    theless
    0.16
    ãĤīãģĦ
    0.16
    wegian
    0.16
    ctal
    0.15
     necessarily
    0.15
     tamp
    0.15
    thern
    0.15
    Act Density 0.022%

    No Known Activations