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

    Neuronpedia

    INDEX
    Explanations

    the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.05
    2:0.08
    3:0.08
    4:0.09
    5:0.07
    6:0.09
    7:0.08
    8:0.08
    9:0.07
    10:0.09
    11:0.08
    Negative Logits
    trak
    -1.96
    raped
    -1.85
    imeo
    -1.77
    REP
    -1.76
    acted
    -1.76
    ishly
    -1.73
    agonist
    -1.72
    edom
    -1.71
     harassed
    -1.67
    apesh
    -1.66
    POSITIVE LOGITS
     WW
    1.76
     HW
    1.71
     Ecc
    1.68
     Ends
    1.68
     Tah
    1.67
     Springer
    1.66
     averages
    1.64
     Zurich
    1.63
     Precision
    1.59
     classics
    1.59
    Act Density 0.000%

    No Known Activations