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

    Neuronpedia

    INDEX
    Explanations

    the concept of singularity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     belts
    -2.55
     gearing
    -2.41
    ected
    -2.38
     engineered
    -2.35
     widened
    -2.31
     portraying
    -2.29
    ](
    -2.22
     mantle
    -2.17
     ruled
    -2.16
     overseeing
    -2.14
    POSITIVE LOGITS
    Submit
    2.88
     trave
    2.58
    Mine
    2.47
     contrace
    2.46
     exha
    2.34
     experien
    2.32
     predec
    2.28
     Mine
    2.25
     INST
    2.22
     Exile
    2.22
    Act Density 0.000%

    No Known Activations