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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal identity and societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by forms of "become"

    np_acts-logits-general · gemini-2.0-flash

    becoming something else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gehad
    -0.64
    sidian
    -0.61
     داشتند
    -0.59
    Personensuche
    -0.56
    providedIn
    -0.52
     دارند
    -0.48
     داشتم
    -0.48
     avoient
    -0.48
     دارد
    -0.48
    󠁿
    -0.47
    POSITIVE LOGITS
     become
    3.35
     becomes
    3.09
     becoming
    3.05
    become
    2.90
     Become
    2.87
     became
    2.82
    becoming
    2.66
    becomes
    2.61
    Become
    2.61
     Becoming
    2.60
    Act Density 0.788%

    No Known Activations