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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a state-of-the-art quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -valu
    -0.15
    pants
    -0.15
    tae
    -0.15
    uti
    -0.15
    poke
    -0.15
    uito
    -0.14
     Armour
    -0.14
    753
    -0.14
    pray
    -0.14
    اسطة
    -0.14
    POSITIVE LOGITS
    etimes
    0.17
    oth
    0.16
    dm
    0.15
    ré
    0.14
     Tham
    0.14
    iid
    0.13
     protected
    0.13
    isser
    0.13
     Neo
    0.13
     Eigen
    0.13
    Act Density 0.005%

    No Known Activations