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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating usage or habitual actions

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

    former states or habits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hyrchwyd
    -0.45
     nahilalakip
    -0.45
    Hentet
    -0.43
    XmlAccessorType
    -0.41
    lccn
    -0.41
    Климат
    -0.40
    ParallelGroup
    -0.38
    ⤹
    -0.36
    ]=>
    -0.35
    bootstrapcdn
    -0.35
    POSITIVE LOGITS
     formerly
    0.84
     Formerly
    0.80
    formerly
    0.74
    Formerly
    0.74
     former
    0.71
    former
    0.70
     vroeger
    0.70
     früher
    0.69
     kiedyś
    0.64
     раньше
    0.63
    Act Density 0.087%

    No Known Activations