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

    Neuronpedia

    INDEX
    Explanations

    the word "whether" indicating choices or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stin
    -0.16
    swick
    -0.14
    jo
    -0.14
     ancak
    -0.14
    uir
    -0.14
    roid
    -0.13
     initData
    -0.13
    sv
    -0.13
     Shan
    -0.13
    846
    -0.13
    POSITIVE LOGITS
     it
    0.23
     they
    0.19
     célib
    0.18
     itu
    0.17
     directly
    0.17
    å®ĥ
    0.16
     via
    0.16
     be
    0.16
     you
    0.15
    LTR
    0.14
    Act Density 0.016%

    No Known Activations