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

    Neuronpedia

    INDEX
    Explanations

    references to publication details, particularly volume and page numbers in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()}>
    -0.58
    }>
    -0.57
    <eos>
    -0.56
    ...
    -0.55
    })-
    -0.55
    外部連結
    -0.53
    "}>
    -0.53
    ↵
    -0.52
    ())){
    -0.52
     Schles
    -0.51
    POSITIVE LOGITS
     pp
    1.80
    pp
    1.25
     Pp
    1.14
     PP
    1.05
    PP
    1.03
    Pp
    1.01
    msgSender
    0.96
    ppc
    0.93
     Sepp
    0.92
    躇
    0.85
    Act Density 0.081%

    No Known Activations