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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparison and specifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparisons and acknowledgments in data or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    They
    -0.83
    they
    -0.72
     They
    -0.68
     apiece
    -0.62
    MpServer
    -0.57
    pic
    -0.55
    These
    -0.55
    aire
    -0.55
    kees
    -0.53
     THEY
    -0.52
    POSITIVE LOGITS
     its
    1.44
     Its
    1.11
    Its
    0.90
     ITS
    0.89
    its
    0.88
     everything
    0.84
     all
    0.76
     the
    0.76
     itself
    0.74
     any
    0.73
    Act Density 0.585%

    No Known Activations