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

    Neuronpedia

    INDEX
    Explanations

    words related to alienation and its effects on individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.05
    3:0.06
    4:0.16
    5:0.02
    6:0.03
    7:0.44
    8:0.02
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    pleted
    -1.77
    agate
    -1.70
    estyles
    -1.55
     deeds
    -1.54
    tackle
    -1.53
    ulton
    -1.50
    ultane
    -1.50
     recover
    -1.44
    aughters
    -1.42
    eways
    -1.39
    POSITIVE LOGITS
     sensibilities
    1.84
     Pakistani
    1.53
     Lank
    1.49
     Pakistan
    1.45
     Bangl
    1.43
     unwelcome
    1.42
     Brune
    1.42
    cos
    1.37
     Chomsky
    1.37
     Beng
    1.36
    Act Density 0.002%

    No Known Activations