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

    Neuronpedia

    INDEX
    Explanations

    phrases related to internet regulation and security concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.18
     discharged
    -0.16
     discharge
    -0.15
    phetamine
    -0.15
    èªł
    -0.14
    arias
    -0.14
    ÑĥÑĩаÑģ
    -0.14
     blown
    -0.14
     Redistributions
    -0.14
    avr
    -0.13
    POSITIVE LOGITS
     blocking
    0.31
     blocked
    0.31
     filtering
    0.30
     content
    0.28
     blocks
    0.28
     block
    0.27
    blocked
    0.27
     Blocked
    0.27
     censor
    0.27
    blocking
    0.27
    Act Density 0.034%

    No Known Activations