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

    Neuronpedia

    INDEX
    Explanations

    characters and terms in a foreign language

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.93
    milo
    -0.90
     Pwr
    -0.90
     Seym
    -0.88
    wana
    -0.87
     mathemat
    -0.81
     hitch
    -0.81
     reconc
    -0.81
    ammy
    -0.79
    enegger
    -0.75
    POSITIVE LOGITS
    âĸ¬âĸ¬
    1.32
    âĸ¬
    1.04
    âĶĢâĶĢâĶĢâĶĢ
    1.01
    ¬
    0.91
    âĶĢâĶĢ
    0.83
    ward
    0.81
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.80
    vre
    0.76
    cy
    0.73
    ////////////////////////////////
    0.73
    Act Density 0.013%

    No Known Activations