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

    Neuronpedia

    INDEX
    Explanations

    numerical and technical elements or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fucking
    -0.18
     FUCK
    -0.16
     fucking
    -0.15
    adian
    -0.14
     fucked
    -0.14
    Å¡lo
    -0.14
    SetActive
    -0.14
    thane
    -0.14
    recated
    -0.14
    duk
    -0.14
    POSITIVE LOGITS
     Keynes
    0.16
     stat
    0.15
    าà¸Ĭ
    0.15
     statist
    0.15
     moo
    0.14
    gaard
    0.14
    ons
    0.14
    gle
    0.14
     Mitchell
    0.14
     policies
    0.13
    Act Density 0.001%

    No Known Activations