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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "become" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Langue
    -0.73
     nadzieję
    -0.71
     '\''
    -0.70
     faptul
    -0.68
     căr
    -0.67
     pattes
    -0.67
    待って
    -0.67
     giuri
    -0.65
    insegna
    -0.65
    rektur
    -0.65
    POSITIVE LOGITS
     become
    1.38
     becoming
    1.37
     became
    1.30
     becomes
    1.29
    becomes
    1.24
     Becomes
    1.21
     Becoming
    1.20
    becoming
    1.20
    Become
    1.19
    become
    1.19
    Act Density 0.056%

    No Known Activations