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

    Neuronpedia

    INDEX
    Explanations

    the presence of the pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.08
    3:0.07
    4:0.09
    5:0.07
    6:0.06
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     Saud
    -2.90
    �
    -2.68
    女
    -2.64
     dysph
    -2.60
     Sins
    -2.60
    【
    -2.55
     ¯
    -2.52
     Roses
    -2.51
    ebted
    -2.50
     Sever
    -2.49
    POSITIVE LOGITS
     broadcasters
    2.69
     astronomy
    2.64
     optics
    2.57
     Accuracy
    2.52
     Cosmos
    2.52
     antennas
    2.51
    ereo
    2.40
    endo
    2.40
     broadcaster
    2.38
     amplified
    2.35
    Act Density 0.000%

    No Known Activations