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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uck
    -0.15
    rys
    -0.14
    aha
    -0.14
    sem
    -0.14
    /tos
    -0.14
     Alf
    -0.14
    _WRAP
    -0.13
     ÐĴол
    -0.13
     NES
    -0.13
     ()->
    -0.13
    POSITIVE LOGITS
    ermo
    0.16
    dden
    0.16
    anium
    0.15
     ëĭ¬
    0.15
    dzi
    0.14
    ndata
    0.14
    aque
    0.13
    HEMA
    0.13
    kelig
    0.13
    nave
    0.13
    Act Density 0.023%

    No Known Activations