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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and related forms that indicate state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.18
    ucas
    -0.17
    igram
    -0.17
    /*č↵
    -0.17
    edReader
    -0.16
    oje
    -0.15
    iou
    -0.15
    alker
    -0.15
    Cpp
    -0.15
    NV
    -0.15
    POSITIVE LOGITS
    rupt
    0.16
    panse
    0.15
    585
    0.15
    urning
    0.15
    g
    0.15
    r
    0.14
    ulkan
    0.14
     Playoff
    0.14
     Catch
    0.14
    idth
    0.14
    Act Density 0.001%

    No Known Activations