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

    Neuronpedia

    INDEX
    Explanations

    topics related to conversations and dialogue

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

    話

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bardier
    -0.43
    estroyer
    -0.42
     Kingston
    -0.42
    orghini
    -0.41
     colorida
    -0.41
     scarlet
    -0.40
     Leth
    -0.40
     ostrich
    -0.40
    genous
    -0.40
     Bec
    -0.39
    POSITIVE LOGITS
    話
    1.90
    话
    1.80
     話
    1.42
     话
    1.35
    的话
    1.16
    的話
    1.10
    話が
    1.10
    話の
    1.09
    話を
    1.07
    話は
    1.00
    Act Density 0.003%

    No Known Activations