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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships and communication dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¯Ł
    -0.14
    reon
    -0.13
    άλ
    -0.13
    ado
    -0.13
    Ø°
    -0.13
    (`↵
    -0.13
    adoo
    -0.13
     ib
    -0.13
    rophe
    -0.12
    ]';↵
    -0.12
    POSITIVE LOGITS
     "
    0.29
    :
    0.29
    ãĢĮæĪij
    0.28
    “ä½ł
    0.27
    “æĪij
    0.25
     “
    0.23
    ãĢĮä½ł
    0.22
    :"
    0.19
    ãĢĮãģĤ
    0.19
     '
    0.19
    Act Density 0.374%

    No Known Activations