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

    Neuronpedia

    INDEX
    Explanations

    words that indicate exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.10
    4:0.09
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.06
    Negative Logits
    ilton
    -2.63
    ?),
    -2.63
    NK
    -2.46
     CT
    -2.43
    >)
    -2.42
     bc
    -2.41
    unknown
    -2.40
    vu
    -2.29
     mk
    -2.26
     cass
    -2.25
    POSITIVE LOGITS
    vernment
    2.91
    gencies
    2.82
     Maintenance
    2.70
    Commerce
    2.63
     liquidity
    2.62
     contingency
    2.61
     Operations
    2.46
    ibaba
    2.46
     staffing
    2.41
     modernization
    2.37
    Act Density 0.000%

    No Known Activations