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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location and state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.09
    3:0.10
    4:0.03
    5:0.04
    6:0.12
    7:0.10
    8:0.10
    9:0.07
    10:0.12
    11:0.10
    Negative Logits
    ®,
    -0.91
     releases
    -0.88
     mant
    -0.88
    ointed
    -0.83
    hol
    -0.80
     flies
    -0.77
     rode
    -0.77
     mash
    -0.77
     mold
    -0.76
     releasing
    -0.76
    POSITIVE LOGITS
    senal
    1.18
     Leban
    1.00
     Colossus
    0.99
    orage
    0.97
    LCS
    0.96
    opolis
    0.94
    ificant
    0.92
     teasp
    0.91
    ModLoader
    0.89
    eatures
    0.88
    Act Density 0.147%

    No Known Activations