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

    Neuronpedia

    INDEX
    Explanations

    the word "in" indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.10
    3:0.09
    4:0.07
    5:0.07
    6:0.08
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    iann
    -2.90
    728
    -2.69
    727
    -2.65
    phia
    -2.56
    hyd
    -2.53
     stockp
    -2.50
    Weather
    -2.50
    ww
    -2.50
    ּ
    -2.48
     flooding
    -2.46
    POSITIVE LOGITS
     Persona
    3.35
     Dane
    3.16
     Essence
    3.08
     Aki
    2.95
     Artist
    2.95
     Dean
    2.92
     Authors
    2.89
     Noir
    2.88
     Elise
    2.87
     Dominic
    2.79
    Act Density 0.000%

    No Known Activations