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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tlement
    -0.70
    ocell
    -0.63
    TRIBUN
    -0.62
     fréqu
    -0.58
    sniff
    -0.57
    rances
    -0.56
    hield
    -0.56
     McColl
    -0.55
    äischen
    -0.55
     Teach
    -0.55
    POSITIVE LOGITS
    WriteBarrier
    0.65
     springfox
    0.61
    InstanceState
    0.57
    protoimpl
    0.53
    󠁿
    0.53
    الإنجليزية
    0.53
    MetaObject
    0.53
    %");
    0.52
     astore
    0.52
     oprot
    0.52
    Act Density 0.178%

    No Known Activations