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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing desire or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ordered
    -0.15
    tif
    -0.15
    edback
    -0.15
     canc
    -0.15
    ean
    -0.14
    ancing
    -0.14
    tsy
    -0.14
    454
    -0.14
    agua
    -0.14
    .sm
    -0.14
    POSITIVE LOGITS
     necessarily
    0.16
    agher
    0.15
     Vale
    0.15
     anymore
    0.15
     Zhao
    0.14
    ढ
    0.14
     ä¸ĸ
    0.14
    .eql
    0.14
    heim
    0.14
    å¢ĥ
    0.14
    Act Density 0.021%

    No Known Activations