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

    Neuronpedia

    INDEX
    Explanations

    phrases that reflect family relationships and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.55
     GeoNames
    -0.55
    ће
    -0.51
    そりゃ
    -0.51
     surely
    -0.51
     خواهند
    -0.51
     خواهید
    -0.50
    ydd
    -0.50
    المكان
    -0.49
     насеље
    -0.49
    POSITIVE LOGITS
     be
    1.96
     soient
    1.35
    Be
    1.28
     Be
    1.28
    be
    1.22
     aient
    1.17
     siano
    1.10
     abbia
    1.08
     puissent
    1.06
     soit
    1.04
    Act Density 0.284%

    No Known Activations