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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate belief, assertion, or suggestion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     colli
    -0.77
     doInBackground
    -0.76
     hierogly
    -0.60
     compt
    -0.60
     cantons
    -0.57
     fumig
    -0.57
     Constantinople
    -0.57
     kasarigan
    -0.56
     ELECTRON
    -0.55
     boneca
    -0.55
    POSITIVE LOGITS
    ]")
    0.65
    ]}{
    0.61
     مشين
    0.60
    tagHelperRunner
    0.57
    ]')
    0.56
    "])
    0.56
     việc
    0.55
    ArgsConstructor
    0.55
    ++)
    0.54
    ]-->
    0.54
    Act Density 0.480%

    No Known Activations