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

    Neuronpedia

    INDEX
    Explanations

    phrases related to illegal or unregulated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itto
    -0.18
     linear
    -0.17
    Linear
    -0.15
    linear
    -0.15
     Linear
    -0.15
    436
    -0.14
    ymi
    -0.14
    vanced
    -0.14
    sgi
    -0.14
    bbe
    -0.14
    POSITIVE LOGITS
     informal
    0.34
     amateur
    0.34
     amateurs
    0.32
     DIY
    0.31
     Amateur
    0.30
     homemade
    0.27
     unofficial
    0.26
    æ°ij
    0.26
     makeshift
    0.25
    inform
    0.25
    Act Density 0.179%

    No Known Activations