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

    Neuronpedia

    INDEX
    Explanations

    information related to different languages or potentially encoding issues

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    blance
    -0.58
     Ambro
    -0.54
    INAL
    -0.52
    emort
    -0.51
    ¿½
    -0.50
    Ö¼
    -0.50
    è£
    -0.48
    ormal
    -0.47
    inctions
    -0.47
    tein
    -0.46
    POSITIVE LOGITS
     Rockets
    0.45
     sqor
    0.44
     BYU
    0.43
    ogle
    0.43
     Columb
    0.43
     Clippers
    0.43
    steamapps
    0.42
    ipeg
    0.42
     Lakers
    0.42
     Blog
    0.41
    Act Density 1.492%

    No Known Activations