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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing numerical values or counts, particularly in comparisons or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     заÑģÑĤÑĥп
    -0.16
    ê¼
    -0.15
     вÑĩ
    -0.14
     минÑĥ
    -0.14
     '/';↵
    -0.14
    ::*
    -0.14
    ]={↵
    -0.14
    #/
    -0.14
     }?>↵
    -0.13
    .LookAndFeel
    -0.13
    POSITIVE LOGITS
     "
    0.43
     '
    0.41
     words
    0.34
     “
    0.32
     terms
    0.32
     ‘
    0.29
    “
    0.26
    words
    0.26
     \"
    0.26
    ãĢĮ
    0.25
    Act Density 0.117%

    No Known Activations