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

    Neuronpedia

    INDEX
    Explanations

    phrases that express positive evaluations of performance or quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RouterModule
    -0.65
    IBarButtonItem
    -0.62
    ISupport
    -0.60
    __(/*!
    -0.60
     unknownFields
    -0.58
     CanadaChoose
    -0.56
     springfox
    -0.53
    Kreuz
    -0.53
    mobileqq
    -0.53
     transférez
    -0.51
    POSITIVE LOGITS
    ########.
    0.72
    inerja
    0.67
     cellpadding
    0.64
    BoxShadow
    0.60
    iarkan
    0.59
     Arbeit
    0.58
     Didi
    0.57
    findpost
    0.57
    мені
    0.56
     job
    0.56
    Act Density 0.114%

    No Known Activations