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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or decisions involving social, political, or financial implications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the opening parenthesis symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wildlife
    -0.74
     therap
    -0.72
     intensive
    -0.72
     artisan
    -0.72
     nutrient
    -0.71
     retard
    -0.69
     lull
    -0.68
     inund
    -0.67
     flow
    -0.67
     millenn
    -0.66
    POSITIVE LOGITS
    sic
    1.45
    albeit
    1.44
    including
    1.44
    although
    1.41
    perhaps
    1.39
    possibly
    1.37
    which
    1.37
    usually
    1.34
    especially
    1.34
    see
    1.33
    Act Density 0.206%

    No Known Activations