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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advanced technology or state-of-the-art innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .slim
    -0.17
    _mE
    -0.17
    icum
    -0.16
    _mB
    -0.15
    umont
    -0.15
    AtA
    -0.15
    iêu
    -0.14
    æĤī
    -0.14
    umo
    -0.13
    تدÙī
    -0.13
    POSITIVE LOGITS
     leading
    0.31
    leading
    0.30
    -edge
    0.29
     edge
    0.28
     cutting
    0.23
    edge
    0.23
    -leading
    0.22
     Leading
    0.22
    Leading
    0.21
    /latest
    0.21
    Act Density 0.008%

    No Known Activations