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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.81
    Personensuche
    -0.80
    Datuak
    -0.70
    principalColumn
    -0.67
     endeavouring
    -0.62
    ItemBackground
    -0.61
     attempting
    -0.61
     buscando
    -0.60
     refusing
    -0.57
     seeking
    -0.56
    POSITIVE LOGITS
     part
    0.51
    friend
    0.49
     honest
    0.47
     yourself
    0.44
     competitive
    0.44
     reminded
    0.42
     proactive
    0.41
     assertive
    0.40
     ולה
    0.40
     exact
    0.39
    Act Density 0.292%

    No Known Activations