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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "we" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lccn
    -0.49
    bootstrapcdn
    -0.49
    Kjelder
    -0.47
     propOrder
    -0.46
    RetentionPolicy
    -0.46
    fahan
    -0.46
    AddTagHelper
    -0.46
    uroy
    -0.45
    mistic
    -0.45
    ScopeManager
    -0.44
    POSITIVE LOGITS
     humans
    0.45
     نحن
    0.42
    we
    0.41
     Brits
    0.41
     Filipinos
    0.40
     Europeans
    0.40
    ther
    0.40
    ThroughAttribute
    0.39
    eping
    0.38
    ชาว
    0.37
    Act Density 0.267%

    No Known Activations