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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of absurdity or strangeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.17
    2:0.10
    3:0.06
    4:0.02
    5:0.03
    6:0.17
    7:0.04
    8:0.02
    9:0.21
    10:0.03
    11:0.02
    Negative Logits
    NetMessage
    -3.47
    inventoryQuantity
    -3.19
     Wallet
    -3.01
    cel
    -2.97
     ›
    -2.95
     Sins
    -2.87
    PsyNetMessage
    -2.87
     Gib
    -2.86
    gra
    -2.78
    "]=>
    -2.76
    POSITIVE LOGITS
     bizarre
    5.03
     weird
    4.97
     strange
    4.88
     anomal
    4.62
     Weird
    4.60
     strang
    4.51
     crazy
    4.48
     odd
    4.46
     Strange
    4.37
     surreal
    4.34
    Act Density 0.020%

    No Known Activations