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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and practical examples in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.62
     можуть
    -0.52
     будут
    -0.48
     itself
    -0.48
     umí
    -0.47
     mógł
    -0.46
     هستید
    -0.46
    itself
    -0.46
    himself
    -0.46
     měla
    -0.45
    POSITIVE LOGITS
     ourselves
    0.54
    elemField
    0.52
    SharedDtor
    0.49
    сем
    0.49
     folo
    0.48
     смо
    0.48
    نیم
    0.46
     DAM
    0.45
     говори
    0.45
    ApiModelProperty
    0.44
    Act Density 0.150%

    No Known Activations