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

    Neuronpedia

    INDEX
    Explanations

    words related to quick, abrupt movements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sw" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     negligent
    -0.61
     degrade
    -0.59
    NESS
    -0.58
     DV
    -0.57
    pora
    -0.57
     flawed
    -0.57
    MENT
    -0.56
     preferential
    -0.56
    _-
    -0.55
    ICAL
    -0.55
    POSITIVE LOGITS
    indle
    1.16
    anky
    1.12
    iping
    1.10
    arthy
    1.09
    ipes
    1.06
    immers
    1.06
    itcher
    1.06
    erving
    1.04
    arming
    1.03
    addle
    1.03
    Act Density 0.012%

    No Known Activations