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

    Neuronpedia

    INDEX
    Explanations

    non-zero values or important markers within data or code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -1.17
     RIPRODUZIONE
    -1.10
     Eſ
    -1.06
    вгений
    -1.06
     Efq
    -1.06
     iconFacebook
    -1.04
     CHAPITRE
    -1.04
    IBLIO
    -1.02
     $_"
    -1.01
    ſelf
    -1.01
    POSITIVE LOGITS
    <eos>
    0.74
    　　
    0.61
    <h2>
    0.61
     
    0.58
    ↵↵↵↵
    0.58
    «
    0.58
    <h3>
    0.58
    >>>
    0.55
    ↵
    0.55
    <b>
    0.53
    Act Density 0.171%

    No Known Activations