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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to justification and legitimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thyst
    -0.55
    PullParser
    -0.52
     kiin
    -0.51
    CodeAttribute
    -0.50
    Hentet
    -0.50
    Diwedd
    -0.50
    toolStripButton
    -0.49
     määrä
    -0.48
     sterling
    -0.48
    mbggenerated
    -0.48
    POSITIVE LOGITS
     justify
    1.04
     justifying
    1.03
     justification
    1.03
     justifies
    1.01
     Justification
    0.92
    Justification
    0.88
     excuse
    0.88
     excuses
    0.84
     justified
    0.84
     justific
    0.84
    Act Density 0.343%

    No Known Activations