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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or symbols related to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    h
    -0.20
    tom
    -0.18
     latter
    -0.18
    in
    -0.18
    t
    -0.16
    мом
    -0.16
    D
    -0.15
    A
    -0.15
    nave
    -0.15
    d
    -0.14
    POSITIVE LOGITS
    VERR
    0.17
    ãĥ¼ãĥĵ
    0.16
    (...)↵
    0.15
    ;
    0.14
    :
    0.14
    :↵
    0.14
    amble
    0.14
    riter
    0.13
    greSQL
    0.13
    .TabStop
    0.13
    Act Density 0.024%

    No Known Activations