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

    Neuronpedia

    INDEX
    Explanations

    texts related to promoting respect, appreciation, and positive communication

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-text token, indicating the conclusion of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.59
     Vaugh
    -0.53
    ãĤ©
    -0.52
    eware
    -0.51
    wikipedia
    -0.49
     tabl
    -0.49
    glers
    -0.48
    ãĥĥãĥī
    -0.48
     pse
    -0.48
     blat
    -0.48
    POSITIVE LOGITS
     RELEASE
    0.67
     safely
    0.54
     Xperia
    0.53
    IRE
    0.51
     GeForce
    0.51
     Farming
    0.50
    ¶
    0.50
    Ohio
    0.49
     chars
    0.49
    IAS
    0.49
    Act Density 1.384%

    No Known Activations