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

    Neuronpedia

    INDEX
    Explanations

    gerunds and past participles related to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.05
    4:0.13
    5:0.02
    6:0.03
    7:0.35
    8:0.02
    9:0.04
    10:0.16
    11:0.04
    Negative Logits
    requ
    -1.84
    uctions
    -1.67
    ulla
    -1.66
    ylum
    -1.66
    iques
    -1.63
    pkg
    -1.62
    aceae
    -1.58
    rolet
    -1.54
    lov
    -1.53
    ones
    -1.51
    POSITIVE LOGITS
     gloom
    2.05
     daylight
    1.85
     fireball
    1.76
     Divinity
    1.73
     magnification
    1.70
     cursor
    1.70
     glow
    1.69
     accurately
    1.67
     mir
    1.66
     illusion
    1.65
    Act Density 0.001%

    No Known Activations