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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _LSB
    -0.15
    apon
    -0.15
    aldi
    -0.15
    aux
    -0.14
    ubo
    -0.14
    _native
    -0.13
    cosa
    -0.13
    ita
    -0.13
    éli
    -0.13
     nisi
    -0.13
    POSITIVE LOGITS
     plural
    0.26
     indeed
    0.25
    plural
    0.21
    yes
    0.20
     seriously
    0.19
     mesmo
    0.18
     despite
    0.18
     heard
    0.18
    Indeed
    0.17
     yes
    0.17
    Act Density 0.057%

    No Known Activations