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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "reference" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reference
    -0.79
     Reference
    -0.75
    reference
    -0.73
    Reference
    -0.72
    IndentedString
    -0.69
     références
    -0.69
     REFERENCE
    -0.68
    存于互联网档案馆
    -0.63
    ագրություններ
    -0.60
     CreateTagHelper
    -0.59
    POSITIVE LOGITS
     advances
    0.35
     newName
    0.33
    anz
    0.33
    iddharth
    0.32
     pouvoirs
    0.32
    扱
    0.31
    gun
    0.31
     finger
    0.31
    iss
    0.30
     adoption
    0.30
    Act Density 0.001%

    No Known Activations