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

    Neuronpedia

    INDEX
    Explanations

    character names and their relationships or actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ture
    -0.16
    slideDown
    -0.15
    akeup
    -0.14
     Daly
    -0.14
     Pac
    -0.14
    reau
    -0.14
     Mech
    -0.14
    lord
    -0.14
    ackbar
    -0.14
    lights
    -0.14
    POSITIVE LOGITS
    essler
    0.15
     Malcolm
    0.14
    Construction
    0.14
    ÑĥÑĪ
    0.14
     Ãĺ
    0.14
    igans
    0.14
    Volume
    0.13
    ibel
    0.13
    ulk
    0.13
    construction
    0.13
    Act Density 0.153%

    No Known Activations