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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    oai_token-act-pair · gpt-3.5-turbo

    parentheses or similar bracketed structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isodes
    -0.71
     minded
    -0.69
    leep
    -0.66
    umph
    -0.66
     Tuc
    -0.66
     Champ
    -0.66
     incarn
    -0.65
    entimes
    -0.64
     veterinary
    -0.63
    amily
    -0.63
    POSITIVE LOGITS
    ...)
    1.04
    emphasis
    0.99
    âĢ¦)
    0.87
    ++)
    0.87
    verb
    0.87
     )
    0.86
    ?)
    0.84
    ,)
    0.83
    optional
    0.83
    actual
    0.82
    Act Density 0.062%

    No Known Activations