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

    Neuronpedia

    INDEX
    Explanations

    emotional connections and interactions between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĨłíĨł
    -0.15
    antro
    -0.14
     toxicity
    -0.13
    -Owned
    -0.13
    éĩį大
    -0.13
    reon
    -0.13
     Owned
    -0.12
    ivas
    -0.12
    ãĨ
    -0.12
    andler
    -0.12
    POSITIVE LOGITS
     hap
    0.32
     startled
    0.31
     unsus
    0.30
     eager
    0.29
     unwitting
    0.28
     puzzled
    0.28
     grateful
    0.28
     astonished
    0.28
     bem
    0.28
     frustrated
    0.27
    Act Density 0.535%

    No Known Activations