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

    Neuronpedia

    INDEX
    Explanations

    intense emotional descriptors and superlative expressions

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

    exaggerated positive descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dafx
    -0.54
     público
    -0.38
     scuro
    -0.37
     eventuali
    -0.36
    WSGI
    -0.36
     čas
    -0.36
     część
    -0.35
     związane
    -0.35
    Baca
    -0.35
    requent
    -0.34
    POSITIVE LOGITS
     amazing
    0.94
     incredible
    0.94
     fantastic
    0.91
     awesome
    0.82
    amazing
    0.82
     gorgeous
    0.79
    incredible
    0.78
     marvelous
    0.75
     unbelievable
    0.74
     wonderful
    0.74
    Act Density 0.019%

    No Known Activations