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

    Neuronpedia

    INDEX
    Explanations

    specific monetary values and statistical figures in the given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Whilst
    -1.17
     Whilst
    -1.13
    initialise
    -1.06
     whilst
    -1.03
     recognisable
    -1.02
     initialise
    -0.98
     recognised
    -0.95
     generalised
    -0.94
    Colour
    -0.94
     standardised
    -0.94
    POSITIVE LOGITS
     flavorful
    0.84
     favorite
    0.83
     favorably
    0.82
    favorite
    0.81
    Theater
    0.78
     favor
    0.78
     parlor
    0.78
     ardor
    0.77
     theater
    0.76
     neighborhood
    0.75
    Act Density 6.460%

    No Known Activations