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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal sequences or events that occur after a certain point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enti
    -0.14
    ematik
    -0.14
    aku
    -0.14
    .twimg
    -0.14
    egas
    -0.14
    ONENT
    -0.13
    OGRAPH
    -0.13
    \Has
    -0.13
    eldom
    -0.13
    angen
    -0.13
    POSITIVE LOGITS
     being
    0.35
    being
    0.30
    Being
    0.27
     Being
    0.27
     they
    0.24
    被
    0.23
    -being
    0.23
     it
    0.22
     sendo
    0.20
     essere
    0.19
    Act Density 0.091%

    No Known Activations