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

    Neuronpedia

    INDEX
    Explanations

    references to classes and components in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mund
    -0.17
    anske
    -0.15
    ochen
    -0.15
    ACHINE
    -0.15
    esper
    -0.14
     Verg
    -0.14
    UTH
    -0.14
    ä¸Ī
    -0.14
    agar
    -0.13
    jango
    -0.13
    POSITIVE LOGITS
    dac
    0.17
    Ñijм
    0.15
    igham
    0.15
    ocks
    0.15
    rance
    0.15
    ivist
    0.15
    pitch
    0.14
    еннÑĸ
    0.14
    pcf
    0.14
    acos
    0.14
    Act Density 0.181%

    No Known Activations