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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.15
    2:0.05
    3:0.04
    4:0.04
    5:0.12
    6:0.03
    7:0.05
    8:0.09
    9:0.05
    10:0.05
    11:0.05
    Negative Logits
    Sax
    -1.75
    rb
    -1.54
    ensional
    -1.52
     Nebula
    -1.49
    ‑
    -1.48
    cube
    -1.47
    prints
    -1.47
    bard
    -1.46
    Gal
    -1.46
    laws
    -1.43
    POSITIVE LOGITS
     confir
    1.89
     sidx
    1.84
     enable
    1.79
     exclude
    1.68
    ption
    1.66
    ��
    1.65
    ��
    1.65
    ��
    1.64
     preferred
    1.61
     convert
    1.60
    Act Density 0.009%

    No Known Activations