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

    Neuronpedia

    INDEX
    Explanations

    text written in a foreign language

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     sidx
    -1.03
     reconc
    -1.00
     sqor
    -0.84
    otin
    -0.83
     redund
    -0.81
     snail
    -0.81
    urion
    -0.80
     affidav
    -0.80
    onym
    -0.78
    utenberg
    -0.78
    POSITIVE LOGITS
    Ĥ
    1.14
    Ø©
    1.07
    ¯¯¯¯¯¯¯¯
    1.02
    ļé
    1.01
    ¤
    1.00
    ļ
    0.99
    ¾
    0.99
    Ĩ
    0.99
    Į
    0.97
    ¬
    0.96
    Act Density 0.816%

    No Known Activations