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

    Neuronpedia

    INDEX
    Explanations

    concepts related to organizational structures and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DW
    -0.15
    amo
    -0.14
    gom
    -0.14
    oka
    -0.14
    ereg
    -0.13
    iy
    -0.13
     bo
    -0.13
    LOCKS
    -0.13
     B
    -0.13
    :,
    -0.13
    POSITIVE LOGITS
    raquo
    0.16
    afone
    0.15
    ilinear
    0.15
    upo
    0.15
    vail
    0.14
    icha
    0.14
    ErrorException
    0.14
    akest
    0.14
    alice
    0.14
    aping
    0.14
    Act Density 0.136%

    No Known Activations