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

    Neuronpedia

    INDEX
    Explanations

    specific words related to business and employment agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tran
    -0.17
     Drum
    -0.16
    rum
    -0.16
     Holland
    -0.15
    hek
    -0.15
    aire
    -0.15
    alah
    -0.14
     mass
    -0.14
    xeb
    -0.14
    aginator
    -0.14
    POSITIVE LOGITS
    stance
    0.17
    erview
    0.15
    umbo
    0.15
    ?a
    0.14
    ELLOW
    0.14
    ourke
    0.14
    IM
    0.13
    pector
    0.13
    v
    0.13
    emet
    0.13
    Act Density 0.036%

    No Known Activations