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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing experiences or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IBarButtonItem
    -0.82
    ScopeManager
    -0.77
    tualmente
    -0.76
    /***/
    -0.74
     Burrows
    -0.74
    getColumnIndex
    -0.73
    بول
    -0.73
    DebuggerStep
    -0.72
     boisson
    -0.70
    {}{}
    -0.70
    POSITIVE LOGITS
     nice
    1.48
     NICE
    1.45
    NICE
    1.39
     Nice
    1.35
    nice
    1.33
    Nice
    1.25
     nicer
    1.11
     pleasant
    0.99
     nicest
    0.97
     nic
    0.93
    Act Density 0.037%

    No Known Activations