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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or experiences related to relationships

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

    stories recounted not happened

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that occur at the start of a sentence or turn (sentence/turn-initial words and markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.53
     فريبيس
    -0.53
     spesa
    -0.51
     /\.
    -0.50
     comuniques
    -0.47
    ValueStyle
    -0.47
    Cyfeiriadau
    -0.46
     Italijani
    -0.46
    ifikationer
    -0.45
    Попис
    -0.44
    POSITIVE LOGITS
     recounts
    0.45
     Roskov
    0.40
     stories
    0.39
     recounted
    0.39
    awaiter
    0.38
     tales
    0.38
    story
    0.37
    nu
    0.37
     relatos
    0.37
     tale
    0.36
    Act Density 0.049%

    No Known Activations