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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating perception or awareness of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouns
    -0.16
     Ade
    -0.14
    oul
    -0.14
    νια
    -0.14
     Senior
    -0.14
    outil
    -0.13
    quette
    -0.13
    inary
    -0.13
    otal
    -0.13
    tout
    -0.13
    POSITIVE LOGITS
    arkin
    0.16
    afone
    0.15
     caliber
    0.15
    radu
    0.14
    erland
    0.14
    atır
    0.14
    å®Ĺ
    0.14
    currentColor
    0.14
     Buna
    0.13
    ONUS
    0.13
    Act Density 0.116%

    No Known Activations