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

    Neuronpedia

    INDEX
    Explanations

    measurements or technical details

    oai_token-act-pair · gpt-3.5-turbo

    the presence of special symbols or characters, specifically "ÃĹ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -1.00
     ''
    -0.91
     ``
    -0.74
     Prescott
    -0.73
     Frankfurt
    -0.69
     Directorate
    -0.62
     deferred
    -0.62
     Tobacco
    -0.62
    oration
    -0.61
     ....
    -0.61
    POSITIVE LOGITS
    ÃĹ
    3.61
    âĢ³
    1.31
    x
    1.24
    xb
    1.02
    âĢ²
    1.01
    Advertisements
    0.96
    xff
    0.95
    ±
    0.94
    xd
    0.94
    Untitled
    0.91
    Act Density 0.009%

    No Known Activations