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

    Neuronpedia

    INDEX
    Explanations

    expressions of enthusiasm or positive evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lawler
    -0.67
    forKey
    -0.67
     cerebellum
    -0.65
     ordinaire
    -0.65
    AddWithValue
    -0.64
    CardHeader
    -0.64
     Höchst
    -0.62
    entlig
    -0.62
    хьтан
    -0.61
     Neve
    -0.60
    POSITIVE LOGITS
     Fantastic
    0.99
    fantastic
    0.95
    ally
    0.90
    Fantastic
    0.89
     fantastic
    0.88
     romantic
    0.74
     fanta
    0.73
     FAN
    0.72
    STIC
    0.71
     Romantic
    0.70
    Act Density 0.089%

    No Known Activations