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

    Neuronpedia

    INDEX
    Explanations

    initialization or starting tokens in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.67
    الحياه
    -0.60
    DMETHOD
    -0.60
    PyExc
    -0.57
    fhir
    -0.56
    isContained
    -0.56
    izr
    -0.56
     resistência
    -0.55
    Spoljašnje
    -0.55
     resistenza
    -0.54
    POSITIVE LOGITS
    BeginContext
    0.60
    discussion
    0.58
     discussion
    0.57
    órum
    0.55
    FLU
    0.54
     Discussion
    0.53
    onalds
    0.51
     Baumann
    0.51
    |+
    0.49
     critic
    0.49
    Act Density 0.081%

    No Known Activations