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

    Neuronpedia

    INDEX
    Explanations

    prominent nouns and phrases indicating significance or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bonds
    -0.15
    åĴ¨
    -0.15
    //{{
    -0.14
    arest
    -0.14
    ajaran
    -0.14
    hai
    -0.14
    shima
    -0.14
    Bow
    -0.13
    /antlr
    -0.13
    vention
    -0.13
    POSITIVE LOGITS
     licensors
    0.14
    nock
    0.14
     descend
    0.14
    werk
    0.14
    ://%
    0.13
    Âŀ
    0.13
    íģ¼
    0.13
     saturn
    0.13
    Manip
    0.13
    bane
    0.13
    Act Density 0.081%

    No Known Activations