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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions and access restrictions

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

    not allowed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rör
    -0.31
     relative
    -0.30
     relying
    -0.30
    fml
    -0.29
     xml
    -0.28
     friv
    -0.28
     결
    -0.28
     Ueb
    -0.28
    ніципалі
    -0.28
     selected
    -0.27
    POSITIVE LOGITS
     prohibited
    0.95
     forbid
    0.93
     prohibit
    0.92
     prohibitions
    0.92
     forbidden
    0.91
     prohibition
    0.90
     forbids
    0.87
     forbade
    0.84
     prohibits
    0.84
    禁止
    0.83
    Act Density 0.083%

    No Known Activations