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

    Neuronpedia

    INDEX
    Explanations

    phrases focusing on the act of speaking or expressing thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Бахар
    -0.71
     rhestr
    -0.70
    cún
    -0.70
    bufio
    -0.67
    EDEFAULT
    -0.65
     reportedly
    -0.60
    ientôt
    -0.60
     Biôgrafia
    -0.60
    HasBeenSet
    -0.59
    esez
    -0.59
    POSITIVE LOGITS
     decir
    0.76
     saying
    0.66
     say
    0.63
     сказать
    0.58
     Saying
    0.58
     للاسماء
    0.57
     BorderSide
    0.54
     mengucapkan
    0.54
    Saying
    0.54
     dizer
    0.53
    Act Density 0.218%

    No Known Activations