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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors indicating quality or pleasantness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.86
    IBarButtonItem
    -0.85
     Burrows
    -0.80
    tedrale
    -0.75
    setVerticalGroup
    -0.75
    JMenuBar
    -0.72
    WithIdentifier
    -0.69
    complexType
    -0.68
    ribune
    -0.68
     NSCoder
    -0.67
    POSITIVE LOGITS
     nice
    2.12
     Nice
    1.83
    nice
    1.82
     NICE
    1.77
    Nice
    1.76
    NICE
    1.67
     nicer
    1.61
     nicest
    1.49
     nicely
    1.36
     pleasant
    1.22
    Act Density 0.038%

    No Known Activations