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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.91
    )_/¯
    -0.90
    "),
    -0.88
    homonymie
    -0.88
    TextBoxColumn
    -0.88
    SerializedSize
    -0.87
    sterious
    -0.87
    Cyfeiriadau
    -0.83
    `,
    -0.83
     Dons
    -0.83
    POSITIVE LOGITS
    Here
    1.95
     Here
    1.95
     here
    1.85
    here
    1.80
     HERE
    1.72
    HERE
    1.54
     aquí
    1.40
     aqui
    1.35
     Aquí
    1.33
    Aqui
    1.30
    Act Density 0.057%

    No Known Activations