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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TextBoxColumn
    -0.91
    homonymie
    -0.87
     Wil
    -0.79
    )_/¯
    -0.78
    SerializedSize
    -0.78
    kosh
    -0.77
     Dons
    -0.77
    StatusLabel
    -0.76
    NameInMap
    -0.76
    [];
    -0.76
    POSITIVE LOGITS
     Here
    1.60
     HERE
    1.57
    Here
    1.55
    here
    1.48
     here
    1.46
    HERE
    1.46
     aquí
    1.23
     aqui
    1.23
     Aquí
    1.21
    Aqui
    1.15
    Act Density 0.058%

    No Known Activations