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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to loss and security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esk
    -0.16
    oy
    -0.14
    åĮ¹
    -0.14
    ourke
    -0.14
    ortex
    -0.14
    lendi
    -0.13
    SetBranch
    -0.13
    .localtime
    -0.13
    Å¡em
    -0.13
    ëŁŃ
    -0.13
    POSITIVE LOGITS
    irket
    0.15
    ane
    0.14
    .authentication
    0.14
    924
    0.14
     hala
    0.13
     animation
    0.13
    553
    0.13
     Buk
    0.13
    amble
    0.13
    idend
    0.13
    Act Density 0.388%

    No Known Activations