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

    Neuronpedia

    INDEX
    Explanations

    instances of interruptions and conversational dynamics in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atr
    -0.16
    èĢĥ
    -0.15
    shaw
    -0.15
    oms
    -0.15
    oto
    -0.14
    led
    -0.14
    ibold
    -0.14
    orex
    -0.14
    llum
    -0.14
     missions
    -0.13
    POSITIVE LOGITS
    INET
    0.16
    inet
    0.14
    ertype
    0.14
    eker
    0.14
    hec
    0.14
    piler
    0.14
     Kemp
    0.14
    ãĥĥãĥĦ
    0.14
    anford
    0.14
    VRT
    0.13
    Act Density 0.311%

    No Known Activations