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

    Neuronpedia

    INDEX
    Explanations

    references to code elements or types in programming discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folio
    -0.17
    querque
    -0.16
    owie
    -0.16
    antry
    -0.15
    ableView
    -0.15
     Immutable
    -0.15
    berman
    -0.14
    ooth
    -0.14
    abee
    -0.14
    erton
    -0.14
    POSITIVE LOGITS
    иÑģÑĤÑĢа
    0.15
     Judges
    0.15
     unsupported
    0.14
     ning
    0.14
    rawl
    0.13
     Pra
    0.13
    ëį
    0.13
     Grove
    0.13
    sburg
    0.13
    Ñĥй
    0.13
    Act Density 0.000%

    No Known Activations