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

    Neuronpedia

    INDEX
    Explanations

    exclamatory phrases or interjections

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific symbols or characters, particularly the "âĢ" sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.85
    ESSION
    -0.80
    ividual
    -0.72
     redist
    -0.72
     prevailing
    -0.68
     disparate
    -0.67
     confir
    -0.67
    mercial
    -0.66
     telecommunications
    -0.65
     Samoa
    -0.65
    POSITIVE LOGITS
    dro
    1.07
    âĢķ
    1.01
    ¹
    1.00
    £
    0.95
    º
    0.90
    Ń
    0.89
    ½
    0.87
    ¡
    0.86
    say
    0.85
    ª
    0.85
    Act Density 0.352%

    No Known Activations