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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    oai_token-act-pair · gpt-3.5-turbo

    the presence of parentheses or brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leep
    -0.75
     minded
    -0.73
     Renew
    -0.68
     smelling
    -0.67
    ettings
    -0.65
    umph
    -0.65
     wing
    -0.64
     packaging
    -0.64
    isodes
    -0.63
    apy
    -0.63
    POSITIVE LOGITS
    ...)
    1.03
    emphasis
    0.93
    ?)
    0.90
    !)
    0.90
    âĢ¦)
    0.89
    actual
    0.88
    ,)
    0.87
    ++)
    0.87
    *)
    0.87
     )
    0.86
    Act Density 0.072%

    No Known Activations