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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "for" and its associated phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.42
    7:0.03
    8:0.06
    9:0.07
    10:0.07
    11:0.05
    Negative Logits
     Channel
    -1.38
     Cly
    -1.36
    ktop
    -1.30
     orphans
    -1.18
     Picks
    -1.10
     lil
    -1.09
     Brill
    -1.08
    FTWARE
    -1.04
     knot
    -1.04
     Horde
    -1.04
    POSITIVE LOGITS
    ��
    1.79
    acus
    1.68
    oux
    1.45
    hene
    1.43
    opa
    1.42
    ón
    1.39
    cedented
    1.38
    inous
    1.38
    assault
    1.37
    utical
    1.36
    Act Density 0.005%

    No Known Activations