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

    Neuronpedia

    INDEX
    Explanations

    elements related to recommendations and positive user experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     invokingState
    -0.66
    DrawerToggle
    -0.60
    unknownFields
    -0.58
    ToMany
    -0.57
    meanor
    -0.54
     bristle
    -0.53
     투
    -0.53
    Atsauces
    -0.53
    NNY
    -0.52
    例句
    -0.52
    POSITIVE LOGITS
     recommend
    0.89
     recommending
    0.85
     recommended
    0.83
     Recommend
    0.81
     Recommended
    0.81
     recommendation
    0.77
     recomend
    0.75
     reccom
    0.73
     RECOMMENDED
    0.72
    ArrowToggle
    0.72
    Act Density 0.092%

    No Known Activations