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

    Neuronpedia

    INDEX
    Explanations

    references to containment and location within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.05
    4:0.09
    5:0.02
    6:0.06
    7:0.42
    8:0.03
    9:0.03
    10:0.06
    11:0.08
    Negative Logits
    evaluate
    -1.49
    uncture
    -1.45
     enthusi
    -1.44
    龍
    -1.44
     direction
    -1.43
    Us
    -1.42
     emulate
    -1.42
    PDATE
    -1.40
     ambassadors
    -1.40
    Ranked
    -1.37
    POSITIVE LOGITS
    complex
    1.54
     Vall
    1.50
    illac
    1.43
     preserves
    1.40
     Pill
    1.38
    mite
    1.33
     Carn
    1.32
     Stat
    1.32
    ngth
    1.30
    oit
    1.29
    Act Density 0.002%

    No Known Activations