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

    Neuronpedia

    INDEX
    Explanations

    references to approval or assessment criteria related to projects or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.10
    3:0.06
    4:0.13
    5:0.03
    6:0.10
    7:0.28
    8:0.03
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     神
    -1.76
     oun
    -1.62
     Learns
    -1.57
     redistributed
    -1.53
     concess
    -1.51
     ├
    -1.50
    soType
    -1.49
    forth
    -1.44
     rgb
    -1.42
     uniquely
    -1.41
    POSITIVE LOGITS
    ources
    1.58
     halls
    1.52
     trenches
    1.50
    roph
    1.50
     ruins
    1.50
     orbit
    1.49
     Canal
    1.45
     recess
    1.44
     Collider
    1.42
     doors
    1.41
    Act Density 0.000%

    No Known Activations