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

    Neuronpedia

    INDEX
    Explanations

    character sequences containing symbols, possibly for code or formatting purposes

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used in formatting or coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eness
    -0.80
    ichick
    -0.74
    adelphia
    -0.72
    omorphic
    -0.70
    kson
    -0.69
    unia
    -0.68
     unlaw
    -0.68
     boards
    -0.68
    inelli
    -0.67
     delinqu
    -0.67
    POSITIVE LOGITS
    âĢ¢âĢ¢
    0.97
    AUT
    0.87
    SK
    0.84
    NEW
    0.81
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.78
    COMPLE
    0.78
    ERROR
    0.77
    insert
    0.77
    PET
    0.77
    laughs
    0.76
    Act Density 0.015%

    No Known Activations