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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to changes, modifications, or adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icoot
    -0.75
    XmlRootElement
    -0.71
     high
    -0.64
    modb
    -0.63
     p
    -0.63
    -
    -0.63
     Jamie
    -0.62
    allowNull
    -0.62
     pyr
    -0.60
    rag
    -0.60
    POSITIVE LOGITS
    تقاوى
    1.10
     themſelves
    0.99
     pleaſure
    0.98
     myſelf
    0.97
     enlargement
    0.94
     worsened
    0.94
     deepened
    0.93
     himſelf
    0.93
     itſelf
    0.92
     Améli
    0.91
    Act Density 0.064%

    No Known Activations