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

    Neuronpedia

    INDEX
    Explanations

    elements of narrative focus on personal struggles and challenges

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

    Follows a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sice
    -0.62
    therefore
    -0.61
    thus
    -0.60
     therefore
    -0.58
     infatti
    -0.56
     zwar
    -0.55
    indeed
    -0.53
    esModule
    -0.50
     portanto
    -0.49
    ThemeOverlay
    -0.48
    POSITIVE LOGITS
     nonetheless
    0.97
     nevertheless
    0.93
     ändå
    0.83
     trotzdem
    0.81
    卻
    0.80
     dennoch
    0.78
    一方で
    0.76
    却
    0.75
    terscotch
    0.74
     samtidigt
    0.72
    Act Density 0.514%

    No Known Activations