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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Well" and related conversational fillers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aspers
    -0.17
    illon
    -0.16
    aldi
    -0.16
    phas
    -0.16
    ancell
    -0.15
    侯
    -0.15
    ì¦Ŀ
    -0.15
    elier
    -0.15
    æĬķ注
    -0.15
    çĶ
    -0.14
    POSITIVE LOGITS
    ensch
    0.15
    ipsis
    0.15
    ode
    0.14
    ODE
    0.14
    oding
    0.14
    odes
    0.14
     certainly
    0.14
    onor
    0.13
    aker
    0.13
    odon
    0.13
    Act Density 0.039%

    No Known Activations