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

    Neuronpedia

    INDEX
    Explanations

    specific actions or instructions regarding user interactions on a platform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.47
    发表于
    -0.47
    UnusedPrivate
    -0.47
    nocache
    -0.44
     Wikimedijinoj
    -0.43
    SequentialGroup
    -0.41
     yyb
    -0.41
    Geplaatst
    -0.40
    Outside
    -0.40
    RegressionTest
    -0.40
    POSITIVE LOGITS
     highlighted
    0.91
     icon
    0.87
     icons
    0.84
     pop
    0.82
     popup
    0.80
     displayed
    0.77
     gray
    0.76
     circled
    0.76
     box
    0.76
     arrow
    0.76
    Act Density 0.501%

    No Known Activations