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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "who" in various contexts, often relating to identification or description of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.19
    3:0.09
    4:0.06
    5:0.04
    6:0.03
    7:0.03
    8:0.07
    9:0.04
    10:0.12
    11:0.25
    Negative Logits
    soc
    -1.72
    arts
    -1.71
    ographies
    -1.61
    lists
    -1.53
    hetics
    -1.51
    adium
    -1.50
    eals
    -1.50
    raft
    -1.50
    Soc
    -1.49
    erning
    -1.48
    POSITIVE LOGITS
     projectile
    1.62
     flanked
    1.62
     angered
    1.56
     scapego
    1.53
     unemploy
    1.50
     besie
    1.49
     provoked
    1.46
     forcefully
    1.45
    eatures
    1.45
     annexed
    1.45
    Act Density 0.030%

    No Known Activations