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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.24
    1:0.04
    2:0.03
    3:0.09
    4:0.15
    5:0.09
    6:0.04
    7:0.05
    8:0.07
    9:0.08
    10:0.03
    11:0.04
    Negative Logits
    express
    -1.92
     carbohyd
    -1.84
    ithering
    -1.82
    activ
    -1.81
     destro
    -1.71
    everal
    -1.68
    acers
    -1.68
    ansson
    -1.67
     referen
    -1.65
    ÃÂ
    -1.62
    POSITIVE LOGITS
     Population
    2.12
    =-=-=-=-=-=-=-=-
    1.92
    /-
    1.91
    /(
    1.81
    /+
    1.78
     Number
    1.74
     Weak
    1.68
     Rating
    1.67
     Rape
    1.66
     Highest
    1.66
    Act Density 0.005%

    No Known Activations