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

    Neuronpedia

    INDEX
    Explanations

    phrases pertaining to honesty and transparency in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.77
    principalTable
    -0.65
    Enllaces
    -0.65
    ChildIndex
    -0.63
    Jeografia
    -0.60
    zwungen
    -0.60
    rhosis
    -0.59
     صوتيه
    -0.59
    WireFormat
    -0.58
    GeneratedValue
    -0.54
    POSITIVE LOGITS
     caution
    0.76
     caveats
    0.74
     disclaimer
    0.72
     warn
    0.72
     warning
    0.71
     warnings
    0.71
     cautions
    0.65
     upfront
    0.64
     caveat
    0.64
     cautioned
    0.63
    Act Density 0.386%

    No Known Activations