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

    Neuronpedia

    INDEX
    Explanations

    reviews of dining experiences and food quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.72
    StoryboardSegue
    -0.61
    NgModule
    -0.60
    انيف
    -0.60
    IndentedString
    -0.59
    esModule
    -0.58
    InputBorder
    -0.58
    HtmlAttribute
    -0.56
    хьтан
    -0.53
     IBOutlet
    -0.53
    POSITIVE LOGITS
     wise
    0.77
     itself
    0.74
     sucked
    0.74
     excellent
    0.70
     superb
    0.69
     sucks
    0.68
     fantastic
    0.67
     AMAZING
    0.67
     outstanding
    0.66
     exceptional
    0.66
    Act Density 0.162%

    No Known Activations