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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.09
    3:0.28
    4:0.02
    5:0.02
    6:0.13
    7:0.08
    8:0.05
    9:0.10
    10:0.06
    11:0.06
    Negative Logits
    ngth
    -1.41
    alore
    -1.40
    glers
    -1.37
    bably
    -1.35
    yrinth
    -1.32
    heastern
    -1.31
    enhagen
    -1.29
    eele
    -1.27
    kefeller
    -1.18
    heast
    -1.16
    POSITIVE LOGITS
    asca
    1.40
    ه
    1.29
    NI
    1.26
    angel
    1.16
    Zen
    1.15
    ر
    1.11
    ENA
    1.10
    ía
    1.09
    ahu
    1.08
    ة
    1.08
    Act Density 0.005%

    No Known Activations