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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legality and justifications for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ander
    -0.16
    kses
    -0.16
    _tls
    -0.14
    è©
    -0.14
    _crit
    -0.14
    ãĥ¼ãĥĵ
    -0.13
     Reality
    -0.13
    æ³ģ
    -0.13
    Æ°á»Ľ
    -0.13
    FFE
    -0.13
    POSITIVE LOGITS
     reasons
    0.63
     Reasons
    0.50
     reason
    0.37
    reason
    0.35
     fear
    0.34
    åİŁåĽł
    0.31
    Reason
    0.31
    _reason
    0.28
     purposes
    0.26
    çIJĨçĶ±
    0.26
    Act Density 0.175%

    No Known Activations