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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or structural elements in the text, particularly those related to citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    albert
    -0.80
    рян
    -0.74
    fout
    -0.72
    [toxicity=0]
    -0.70
     Blak
    -0.70
    viel
    -0.70
    lık
    -0.69
     Raton
    -0.69
     ASE
    -0.67
    inode
    -0.67
    POSITIVE LOGITS
     ¡¡
    1.15
     wikipagina
    0.91
    )**
    0.89
    (**
    0.88
    .**
    0.86
    /****
    0.86
    ]**
    0.81
    kwargs
    0.80
    ¡¡
    0.79
    {!!
    0.78
    Act Density 0.349%

    No Known Activations