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

    Neuronpedia

    INDEX
    Explanations

    code expressions related to programming constructs or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.66
     مرئيه
    -0.61
    RTGC
    -0.56
    ⤹
    -0.55
     समीक्षक
    -0.54
     stør
    -0.54
     Administrativna
    -0.51
     témoig
    -0.50
    yczą
    -0.50
     ukuran
    -0.50
    POSITIVE LOGITS
     censiti
    0.35
    fucking
    0.35
     Fucking
    0.34
     fucking
    0.33
     prompting
    0.33
    ExecuteReader
    0.32
     Metro
    0.31
    Fucking
    0.31
    maketitle
    0.31
     then
    0.30
    Act Density 0.061%

    No Known Activations