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

    Neuronpedia

    INDEX
    Explanations

    themes related to difficult and undesirable jobs

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سر
    -0.34
     '\\;'
    -0.34
    PreferredItem
    -0.34
     שול
    -0.33
    aites
    -0.33
     шу
    -0.32
     instal
    -0.32
    族
    -0.32
     transpired
    -0.31
     Gregory
    -0.31
    POSITIVE LOGITS
    AutoScaleMode
    0.60
    Tembelea
    0.58
     CanadaChoose
    0.57
     مشين
    0.53
    -------
    0.51
    setVerticalGroup
    0.50
    Derbyniad
    0.50
     soggetto
    0.49
     nød
    0.49
    recated
    0.49
    Act Density 0.034%

    No Known Activations