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

    Neuronpedia

    INDEX
    Explanations

    instances of direct speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldom
    -0.16
    illez
    -0.15
     argued
    -0.15
    ArgumentException
    -0.15
     Warning
    -0.15
     arguments
    -0.14
    _WARNING
    -0.14
     REQ
    -0.14
    iej
    -0.14
     Arg
    -0.14
    POSITIVE LOGITS
     conf
    0.24
     recalled
    0.24
     reveals
    0.22
    reve
    0.22
     confess
    0.22
    recall
    0.22
     admit
    0.21
     revealed
    0.21
     revelation
    0.20
     recalls
    0.20
    Act Density 0.085%

    No Known Activations