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

    Neuronpedia

    INDEX
    Explanations

    concepts related to community spaces and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.01
    3:0.12
    4:0.04
    5:0.20
    6:0.04
    7:0.02
    8:0.12
    9:0.26
    10:0.01
    11:0.02
    Negative Logits
    機
    -2.13
     Baird
    -2.03
     Beir
    -2.02
    �
    -1.96
    884
    -1.83
     Yates
    -1.79
     captcha
    -1.78
     Abbott
    -1.78
    SourceFile
    -1.76
     Hollande
    -1.76
    POSITIVE LOGITS
     creatively
    2.50
     individuality
    2.10
    lesh
    2.05
    rium
    2.05
     responsibly
    2.03
     limitless
    2.03
    ounge
    2.00
     seamlessly
    1.99
     enthusi
    1.99
     freely
    1.98
    Act Density 0.064%

    No Known Activations