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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal documents, authorities, and registration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "LL" within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itutes
    -0.75
    ãĥ¥
    -0.71
    ãĥĹ
    -0.67
    ndra
    -0.66
    opol
    -0.66
    ãĥ£
    -0.65
    cean
    -0.65
    ãĥ¼ãĥĨ
    -0.65
    qua
    -0.65
     laps
    -0.64
    POSITIVE LOGITS
    iard
    1.10
    INGTON
    1.05
    ounge
    1.04
    oyd
    1.02
    ING
    1.00
    uminati
    0.95
    ION
    0.95
    ibrary
    0.94
    BACK
    0.93
    OCK
    0.87
    Act Density 0.015%

    No Known Activations