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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and descriptors related to events or activities involving individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.35
    1:0.05
    2:0.04
    3:0.07
    4:0.05
    5:0.14
    6:0.07
    7:0.02
    8:0.05
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
     relapse
    -1.69
     clipboard
    -1.68
     fallacy
    -1.63
     OCD
    -1.52
    ebin
    -1.50
     payload
    -1.50
     distortion
    -1.50
     miscarriage
    -1.50
     onward
    -1.49
    ificate
    -1.49
    POSITIVE LOGITS
    ONSORED
    1.77
    quartered
    1.70
    VERTIS
    1.60
    Nation
    1.59
    Metro
    1.58
    Legend
    1.56
    offic
    1.56
    ipedia
    1.55
    CHO
    1.55
    wyn
    1.54
    Act Density 0.167%

    No Known Activations