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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and descriptions using the term "in terms of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce comparisons or discussions about different topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.77
    ŃĶ
    -0.71
     exting
    -0.65
    lehem
    -0.63
     Chern
    -0.63
    ogether
    -0.62
     Staten
    -0.62
     Mercy
    -0.61
    ©¶æ
    -0.59
     paran
    -0.58
    POSITIVE LOGITS
     of
    1.19
     thereof
    1.00
     OF
    0.79
    Of
    0.79
    of
    0.79
     Of
    0.75
    eme
    0.72
     regards
    0.72
    aldehyde
    0.69
    pring
    0.69
    Act Density 0.039%

    No Known Activations