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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "working" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    working and related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bondale
    -0.38
     Occidente
    -0.36
    :][
    -0.35
    værk
    -0.33
    sieht
    -0.33
    ppuden
    -0.32
    $_['
    -0.32
     rivales
    -0.32
     mocy
    -0.32
     fontes
    -0.32
    POSITIVE LOGITS
     Working
    0.92
     working
    0.91
    Working
    0.91
    WORKING
    0.86
     WORKING
    0.84
    working
    0.84
     '\\;'
    0.61
    UnusedPrivate
    0.60
     esternos
    0.56
    DockStyle
    0.55
    Act Density 0.019%

    No Known Activations