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

    Neuronpedia

    INDEX
    Explanations

    discussions related to personal experiences and opinions about relationships

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

    preceding modal verbs

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.05
     whoſe
    -0.97
     Majefty
    -0.95
     NDEBUG
    -0.92
    —”
    -0.89
     uſ
    -0.89
     houſe
    -0.88
     ―――――
    -0.88
     Houſe
    -0.88
     ſeveral
    -0.87
    POSITIVE LOGITS
     dont
    1.02
     alot
    0.94
     didnt
    0.93
     loosing
    0.88
     betek
    0.87
     wasnt
    0.83
     doesnt
    0.83
     atleast
    0.81
     wont
    0.80
     realy
    0.80
    Act Density 0.705%

    No Known Activations