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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "this" in various contexts

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

    demonstrative pronoun followed by identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reprodução
    -0.30
     şeyler
    -0.30
    ioutil
    -0.28
    because
    -0.27
     getItemId
    -0.27
    tidumbre
    -0.27
     nombres
    -0.27
     Yii
    -0.26
     patrie
    -0.26
    False
    -0.26
    POSITIVE LOGITS
    ftagPool
    0.81
    󠁢
    0.77
    MarshalTo
    0.73
     delightful
    0.72
    󠁣
    0.71
    AnchorStyles
    0.68
     fascinating
    0.65
     succulent
    0.65
     charming
    0.65
     luxurious
    0.64
    Act Density 0.017%

    No Known Activations