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

    Neuronpedia

    INDEX
    Explanations

    instances of bans and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rips
    -0.14
    ditor
    -0.14
    èħ
    -0.14
    alon
    -0.14
    onica
    -0.13
    LEV
    -0.13
    ivism
    -0.13
    azor
    -0.13
     Vance
    -0.13
    berman
    -0.13
    POSITIVE LOGITS
    cker
    0.17
    eker
    0.15
     access
    0.15
    aise
    0.15
     Voj
    0.14
    Anywhere
    0.14
     participant
    0.14
     participating
    0.14
     anywhere
    0.13
     privilege
    0.13
    Act Density 0.093%

    No Known Activations