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

    Neuronpedia

    INDEX
    Explanations

    instances referring to events or situations that occur after a significant incident or emergency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walsh
    -0.16
    cki
    -0.15
    HEET
    -0.15
    cket
    -0.14
    csi
    -0.14
    .Buttons
    -0.13
     wouldn
    -0.13
    .idea
    -0.13
     Wouldn
    -0.13
    summ
    -0.13
    POSITIVE LOGITS
    lore
    0.15
    bine
    0.15
    trail
    0.14
    LANGUAGE
    0.14
    addle
    0.13
    path
    0.13
    kick
    0.13
    RuntimeObject
    0.13
    elon
    0.13
    cloak
    0.13
    Act Density 0.010%

    No Known Activations