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

    Neuronpedia

    INDEX
    Explanations

    references to specific events and venues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cats
    -0.15
     Narc
    -0.15
     Homo
    -0.14
    fk
    -0.14
    lava
    -0.14
     sama
    -0.14
     Flint
    -0.14
    adora
    -0.14
    labs
    -0.13
     hiring
    -0.13
    POSITIVE LOGITS
     Staples
    0.24
     Rogers
    0.23
     TD
    0.22
     Scot
    0.21
     Soldier
    0.20
     Stub
    0.19
     ATT
    0.19
     Levi
    0.19
     Stap
    0.19
    TD
    0.19
    Act Density 0.054%

    No Known Activations