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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate historical documentation or records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    のこと
    -0.55
     way
    -0.53
    Véxase
    -0.49
    각주
    -0.49
    ніципа
    -0.48
    ASE
    -0.47
     kaynağından
    -0.46
     taba
    -0.46
     T
    -0.46
    aderas
    -0.45
    POSITIVE LOGITS
    +#+#
    0.75
    AsUp
    0.73
    THISDAY
    0.69
     Où
    0.68
    脚注の使い方
    0.68
    ніципалі
    0.67
     stället
    0.66
    ниципа
    0.66
    WriteTagHelper
    0.66
    cèse
    0.64
    Act Density 0.354%

    No Known Activations