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

    Neuronpedia

    INDEX
    Explanations

    concepts related to addiction and being trapped in negative cycles

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

    Being enticed or trapped

    np_acts-logits-general · gemini-2.0-flash

    drawn into temptation or trap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.58
     незавершена
    -0.52
    canestro
    -0.51
    richTextPanel
    -0.47
     maxn
    -0.46
     bangs
    -0.45
     فريبيس
    -0.42
    complexContent
    -0.42
    tangentMode
    -0.41
     GenerationType
    -0.41
    POSITIVE LOGITS
     seduced
    0.55
     succumbed
    0.50
     succumb
    0.49
     addicted
    0.48
     hooked
    0.47
     apaixon
    0.45
     distracted
    0.45
     temptation
    0.45
     lured
    0.45
     trap
    0.44
    Act Density 0.265%

    No Known Activations