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

    Neuronpedia

    INDEX
    Explanations

    elements related to social interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alui
    -0.47
    在于
    -0.46
    しまう
    -0.46
     generell
    -0.40
     incorporation
    -0.40
     бывает
    -0.40
    XmlEnum
    -0.40
     бывают
    -0.40
     Remains
    -0.39
     blieben
    -0.39
    POSITIVE LOGITS
     doing
    1.14
     trying
    1.14
     enjoying
    1.08
     performing
    1.02
     waiting
    0.99
     attempting
    0.98
     looking
    0.97
     preparing
    0.94
     awaiting
    0.93
    trying
    0.93
    Act Density 0.593%

    No Known Activations