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

    Neuronpedia

    INDEX
    Explanations

    term-based activities and reports, particularly those involving public service or community actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.10
    3:0.07
    4:0.06
    5:0.04
    6:0.05
    7:0.29
    8:0.04
    9:0.05
    10:0.06
    11:0.14
    Negative Logits
    elin
    -1.59
    bold
    -1.45
    mor
    -1.44
    orn
    -1.42
    oot
    -1.38
    urus
    -1.38
    ツ
    -1.37
    fore
    -1.37
    dor
    -1.36
    :{
    -1.35
    POSITIVE LOGITS
     attendance
    1.58
    psey
    1.56
     initiation
    1.55
     session
    1.50
     Psy
    1.46
     etiquette
    1.45
    ysis
    1.42
    lication
    1.41
     Appearance
    1.39
     sessions
    1.38
    Act Density 0.001%

    No Known Activations