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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or evaluations of complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.06
    3:0.06
    4:0.04
    5:0.03
    6:0.22
    7:0.04
    8:0.04
    9:0.23
    10:0.04
    11:0.03
    Negative Logits
     ¯
    -3.54
     Trout
    -3.36
     Leigh
    -3.35
    marg
    -3.32
     ja
    -3.28
     Sig
    -3.27
     Peer
    -3.27
     Levi
    -3.27
     Ralph
    -3.27
     marg
    -3.21
    POSITIVE LOGITS
     Complex
    6.61
     complexes
    6.31
    complex
    5.91
     compound
    5.49
     complex
    5.38
    plex
    5.15
     compounds
    4.73
     complexity
    3.90
     Cosmos
    3.84
    MX
    3.83
    Act Density 0.002%

    No Known Activations