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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pre
    -0.45
    /***/
    -0.44
     besos
    -0.41
    aw
    -0.41
     pre
    -0.39
    Mem
    -0.39
     Always
    -0.39
    case
    -0.39
    f
    -0.38
    ู่
    -0.38
    POSITIVE LOGITS
    lessness
    0.82
    AndEndTag
    0.76
    lorette
    0.76
     <>",
    0.75
    lessly
    0.75
    UnusedPrivate
    0.72
    новниш
    0.71
    verwijspagina
    0.67
    lapsible
    0.67
    LESS
    0.67
    Act Density 1.977%

    No Known Activations