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

    Neuronpedia

    INDEX
    Explanations

    punctuations and special characters often used in digital communication

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -1.12
    WriteBarrier
    -1.05
    Hentet
    -1.02
    httphttps
    -0.96
    তথ্যসূত্র
    -0.93
    /**
    -0.92
     AssemblyTitle
    -0.91
     ostavi
    -0.91
    InjectAttribute
    -0.91
    发表于
    -0.88
    POSITIVE LOGITS
    .
    0.60
    n
    0.53
    ,
    0.49
    lo
    0.49
    S
    0.49
    N
    0.49
    us
    0.45
    ↵↵
    0.45
    o
    0.44
    1
    0.44
    Act Density 0.002%

    No Known Activations