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

    Neuronpedia

    INDEX
    Explanations

    references to sourcing or citing information and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hled
    -0.47
    <eos>
    -0.45
     https
    -0.44
     soin
    -0.43
    haupt
    -0.42
     create
    -0.41
     fully
    -0.40
    illan
    -0.40
     A
    -0.40
     created
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.88
    protoimpl
    0.84
    ConstraintMaker
    0.82
     ProtoMessage
    0.80
     arguments
    0.78
     Superhost
    0.78
     mentioning
    0.78
    ReusableCell
    0.77
     Arguments
    0.76
     uſed
    0.75
    Act Density 0.162%

    No Known Activations