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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "work" and related forms in various contexts

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

    work with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.52
    ConstraintMaker
    -0.51
    GEBURTSDATUM
    -0.43
    ьаж
    -0.43
    aughey
    -0.42
    plaatst
    -0.40
    camis
    -0.40
     duração
    -0.40
    atsun
    -0.39
    zzata
    -0.39
    POSITIVE LOGITS
     dealing
    0.75
     Handling
    0.74
     handling
    0.73
    manip
    0.72
     Umgang
    0.70
    Manip
    0.70
     manip
    0.69
    handling
    0.69
    dealing
    0.69
     Manip
    0.69
    Act Density 0.050%

    No Known Activations