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

    Neuronpedia

    INDEX
    Explanations

    instances of claim and exclusion related to identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,:,
    -0.15
    emode
    -0.15
     COOKIE
    -0.14
     forgiving
    -0.14
    гл
    -0.14
    AxisSize
    -0.14
    ãĥªãĤ«
    -0.14
    averse
    -0.14
    _COMPAT
    -0.14
    ignon
    -0.13
    POSITIVE LOGITS
     participation
    0.31
     participate
    0.30
     join
    0.29
     share
    0.29
     secured
    0.28
    share
    0.28
     shares
    0.27
     sharing
    0.27
     Join
    0.26
     secure
    0.26
    Act Density 0.032%

    No Known Activations