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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the conjunction "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.12
    3:0.05
    4:0.13
    5:0.04
    6:0.20
    7:0.08
    8:0.05
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    (-
    -1.51
    }"
    -1.47
    thens
    -1.42
    Reviewed
    -1.38
     Siber
    -1.37
    Spirit
    -1.37
    :]
    -1.36
     Divinity
    -1.35
     Ago
    -1.32
     Scholar
    -1.32
    POSITIVE LOGITS
     populism
    1.54
    pport
    1.52
    leck
    1.45
     eviction
    1.43
     understatement
    1.40
     coup
    1.39
    DragonMagazine
    1.35
     confusion
    1.32
    osate
    1.29
     hypocrisy
    1.26
    Act Density 0.000%

    No Known Activations