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

    Neuronpedia

    INDEX
    Explanations

    references to various hierarchical structures or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulg
    -0.15
    oined
    -0.15
    [email
    -0.15
    ifes
    -0.14
    /if
    -0.14
    errupt
    -0.14
    uld
    -0.14
    erras
    -0.14
    алеж
    -0.13
    ’t
    -0.13
    POSITIVE LOGITS
     is
    0.25
     has
    0.24
     can
    0.20
     does
    0.17
     cannot
    0.17
     may
    0.16
     will
    0.15
     isn
    0.15
    aire
    0.15
    ìĤ¬ëĬĶ
    0.15
    Act Density 1.568%

    No Known Activations