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

    Neuronpedia

    INDEX
    Explanations

    words related to actions, particularly in legal or employment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    D
    -0.24
    E
    -0.24
    C
    -0.23
    S
    -0.23
    G
    -0.22
    CISION
    -0.18
    O
    -0.17
    SUR
    -0.16
    DEN
    -0.16
    T
    -0.16
    POSITIVE LOGITS
    e
    0.34
    eil
    0.30
    s
    0.28
    eer
    0.27
    eed
    0.24
    eb
    0.23
    eum
    0.23
    t
    0.22
    eve
    0.22
    ei
    0.21
    Act Density 0.049%

    No Known Activations