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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and punctuation within an academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overall
    -0.14
     figure
    -0.13
    oise
    -0.13
    acho
    -0.13
     imper
    -0.13
     table
    -0.13
     PLUS
    -0.13
    elt
    -0.13
    acin
    -0.13
     code
    -0.12
    POSITIVE LOGITS
     Recall
    0.21
     Class
    0.20
     recall
    0.20
     Inform
    0.19
     Define
    0.19
     Explicit
    0.18
     Classical
    0.18
    recall
    0.18
     Classes
    0.18
     Connections
    0.18
    Act Density 0.062%

    No Known Activations