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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    really + adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.65
     EconPapers
    -0.55
     BrowserModule
    -0.54
    RTEE
    -0.52
     ExecuteAsync
    -0.52
     nakalista
    -0.51
    rungsseite
    -0.49
    Rujuakan
    -0.46
     InputDecoration
    -0.46
     MessageBoxIcon
    -0.45
    POSITIVE LOGITS
    really
    0.84
    Really
    0.82
     Really
    0.79
     really
    0.77
     REALLY
    0.73
    weird
    0.60
     weird
    0.57
     messed
    0.53
     guys
    0.53
     Weird
    0.52
    Act Density 0.015%

    No Known Activations