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

    Neuronpedia

    INDEX
    Explanations

    tokens or phrases indicating a transition or change in subject or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thâu
    -0.63
    Становништво
    -0.56
    RRect
    -0.56
    cipar
    -0.56
    NVIC
    -0.53
    ragamo
    -0.51
    __':
    -0.51
    PhysRev
    -0.49
    __':
    -0.49
     ProtoMessage
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.85
     autorytatywna
    0.70
    RegressionTest
    0.62
     lenker
    0.56
    <bos>
    0.55
     kív
    0.55
    ◀
    0.55
     OMITTED
    0.52
     يتيمه
    0.52
    illable
    0.51
    Act Density 0.060%

    No Known Activations