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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or identifiers within technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ìĿ¸
    -0.17
     innings
    -0.16
     ice
    -0.16
     InputStream
    -0.16
    /interfaces
    -0.15
    .intellij
    -0.15
     insects
    -0.15
    ãģĦãģ®
    -0.15
    .invoice
    -0.15
    ake
    -0.15
    POSITIVE LOGITS
    II
    0.19
     II
    0.18
    -II
    0.17
    uja
    0.17
    ilter
    0.17
    OUT
    0.16
    .out
    0.16
    ii
    0.16
    åĩºåı£
    0.15
    OutputStream
    0.15
    Act Density 0.249%

    No Known Activations