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

    Neuronpedia

    INDEX
    Explanations

    references to privacy policies and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ping
    -0.16
    pile
    -0.15
    idak
    -0.14
     pha
    -0.14
     Gamb
    -0.14
    morph
    -0.13
    imon
    -0.13
    mor
    -0.13
    terior
    -0.13
    uest
    -0.13
    POSITIVE LOGITS
     policy
    0.38
     notice
    0.35
     Policy
    0.35
     statement
    0.35
     Statement
    0.32
     Notice
    0.32
    -policy
    0.30
    Policy
    0.29
    _policy
    0.28
    Statement
    0.27
    Act Density 0.018%

    No Known Activations