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

    Neuronpedia

    INDEX
    Explanations

    references to publications or citations, indicating academic or scientific content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿
    -0.17
     ([
    -0.17
    ¾
    -0.16
    3
    -0.15
    ubic
    -0.15
     [
    -0.15
    4
    -0.15
    iq
    -0.14
     p
    -0.14
    okit
    -0.14
    POSITIVE LOGITS
    alias
    0.24
    [][]
    0.22
    [][
    0.21
    elif
    0.16
    adian
    0.16
    developers
    0.15
    elier
    0.15
    {
    0.15
    ads
    0.15
    inspace
    0.15
    Act Density 0.005%

    No Known Activations