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

    Neuronpedia

    INDEX
    Explanations

    expressions involving mathematical symbols, particularly relating to sets and functions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     journalism
    -0.74
     wing
    -0.67
     ranking
    -0.67
     PowerShell
    -0.66
     tackling
    -0.66
     ultr
    -0.65
     entitle
    -0.64
     Tall
    -0.64
     peg
    -0.63
     Rising
    -0.62
    POSITIVE LOGITS
    ...)
    1.33
    âĢ¦)
    1.28
    sic
    1.18
    emphasis
    1.15
    ++)
    1.14
    ,)
    1.14
    ?)
    1.09
    partial
    1.08
    laughs
    1.06
    possibly
    1.06
    Act Density 0.100%

    No Known Activations