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

    Neuronpedia

    INDEX
    Explanations

    the preposition "to" and its various usages in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.07
    4:0.14
    5:0.03
    6:0.08
    7:0.25
    8:0.06
    9:0.05
    10:0.07
    11:0.07
    Negative Logits
     attm
    -1.67
    atari
    -1.53
     Fib
    -1.53
    henko
    -1.49
    nown
    -1.46
     depletion
    -1.38
    agall
    -1.36
    existing
    -1.36
     clause
    -1.34
     Disease
    -1.33
    POSITIVE LOGITS
    umbn
    1.75
    ��
    1.38
    GR
    1.36
    gee
    1.35
     bashing
    1.29
     exorc
    1.27
    �
    1.27
     XD
    1.26
    MIN
    1.26
     Elder
    1.25
    Act Density 0.000%

    No Known Activations