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

    Neuronpedia

    INDEX
    Explanations

    words related to permission or granting authorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    allowing actions or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Back
    -0.47
     Gual
    -0.40
    Sound
    -0.40
    WS
    -0.39
     Zusammenhang
    -0.39
    Looking
    -0.39
    Head
    -0.39
    Down
    -0.38
     “
    -0.38
    They
    -0.38
    POSITIVE LOGITS
     permit
    1.67
     Permit
    1.58
     permits
    1.52
    permit
    1.52
    Permit
    1.46
     Permits
    1.41
     permitting
    1.41
     permitted
    1.40
     PERMIT
    1.34
    permitted
    1.27
    Act Density 0.014%

    No Known Activations