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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to legal and formal declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     personally
    -0.59
     محفوظة
    -0.58
     yourself
    -0.53
     myself
    -0.49
    yourself
    -0.49
     समीक्षाएं
    -0.49
    Yourself
    -0.48
    UpInside
    -0.47
    Conduct
    -0.46
    SELF
    -0.45
    POSITIVE LOGITS
     itself
    1.08
    itself
    0.95
     Itself
    0.92
     للاسماء
    0.74
     its
    0.72
     DbSet
    0.67
     Its
    0.66
     autorytatywna
    0.64
    Its
    0.64
     surla
    0.60
    Act Density 0.856%

    No Known Activations