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

    Neuronpedia

    INDEX
    Explanations

    negative statements and contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tape
    -0.15
    okable
    -0.15
    ulis
    -0.14
    /Dk
    -0.14
    unker
    -0.14
    stre
    -0.14
    urat
    -0.13
    stial
    -0.13
     rat
    -0.13
    ammer
    -0.13
    POSITIVE LOGITS
    eren
    0.17
    alsy
    0.15
    ãĥªãĥ³ãĤ¯
    0.14
     sitesinde
    0.14
    harma
    0.14
    897
    0.14
    ágenes
    0.14
    istrovstvÃŃ
    0.14
    BT
    0.13
     compliment
    0.13
    Act Density 0.193%

    No Known Activations