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

    Neuronpedia

    INDEX
    Explanations

    references to interactions with strangers or public encounters

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

    Interactions with strangers

    np_acts-logits-general · gemini-2.0-flash

    strangers speaking to me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     besluit
    -0.39
     liệt
    -0.38
    TagMode
    -0.36
     initComponents
    -0.36
    nameof
    -0.35
    requireNonNull
    -0.35
    要不
    -0.34
     Spannung
    -0.32
     tetto
    -0.32
     receita
    -0.32
    POSITIVE LOGITS
     passers
    0.64
    󠁬
    0.61
     courte
    0.58
     politely
    0.57
    0.55
     strangers
    0.53
     courteous
    0.52
     snippetHide
    0.52
     pedestrians
    0.52
     motorists
    0.52
    Act Density 0.308%

    No Known Activations