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

    Neuronpedia

    INDEX
    Explanations

    emotional states and concepts related to personal and social challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.04
    2:0.16
    3:0.04
    4:0.05
    5:0.06
    6:0.09
    7:0.02
    8:0.17
    9:0.04
    10:0.09
    11:0.11
    Negative Logits
    ouri
    -1.57
    rb
    -1.54
    ENE
    -1.50
     ABE
    -1.44
    uder
    -1.41
    hower
    -1.41
    itors
    -1.40
    生
    -1.40
    itor
    -1.39
    recated
    -1.39
    POSITIVE LOGITS
    etc
    1.74
     knack
    1.65
     etc
    1.62
     intimacy
    1.53
     compulsion
    1.49
     convictions
    1.48
     CTR
    1.48
     superiority
    1.46
     creativity
    1.43
     charisma
    1.42
    Act Density 0.064%

    No Known Activations