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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaner
    -0.50
    "><?=
    -0.50
    "><?
    -0.46
     ويكيميديا
    -0.46
    freund
    -0.46
    }>{
    -0.45
    sitis
    -0.45
    apunov
    -0.45
    ">{
    -0.44
    apimachinery
    -0.44
    POSITIVE LOGITS
     them
    3.15
     they
    3.06
     They
    2.86
    They
    2.84
     mereka
    2.77
    they
    2.62
    them
    2.49
    Mereka
    2.42
    他们
    2.39
     Mereka
    2.34
    Act Density 1.102%

    No Known Activations