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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     underst
    -0.19
    alus
    -0.16
    issa
    -0.16
     hed
    -0.15
     Hed
    -0.14
    é¾
    -0.14
    ial
    -0.14
    uesta
    -0.14
    ansi
    -0.14
     jur
    -0.14
    POSITIVE LOGITS
    imonials
    0.15
    ër
    0.15
     us
    0.15
     Toll
    0.14
     baiser
    0.14
    redd
    0.14
    inger
    0.14
    λεί
    0.13
    ucus
    0.13
    ulle
    0.13
    Act Density 0.024%

    No Known Activations