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

    Neuronpedia

    INDEX
    Explanations

    phrases related to descriptions of actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calendriers
    -0.56
     بيها
    -0.55
    basicConfig
    -0.52
    AddTagHelper
    -0.52
    "}")
    -0.52
    yó
    -0.51
    Autoritní
    -0.49
    WriteTagHelper
    -0.49
    CloseOperation
    -0.48
    readInt
    -0.48
    POSITIVE LOGITS
     were
    0.77
     are
    0.65
     sembler
    0.63
     they
    0.61
    were
    0.60
     którzy
    0.58
     WERE
    0.57
     belong
    0.56
     viennent
    0.56
     voltak
    0.55
    Act Density 0.789%

    No Known Activations