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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences or codes in a specific format similar to '½' followed by various characters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols typically used in encoding or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.81
    EStreamFrame
    -0.77
    enfranch
    -0.74
     exha
    -0.74
    ufact
    -0.74
     reconc
    -0.73
    ebus
    -0.73
    raints
    -0.73
    ItemImage
    -0.71
    asta
    -0.71
    POSITIVE LOGITS
    ½
    0.97
    ×ķ
    0.87
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.85
    âĶĢâĶĢ
    0.84
    а
    0.83
    ï¸ı
    0.82
    и
    0.82
    ×
    0.82
    ת
    0.81
    е
    0.79
    Act Density 0.006%

    No Known Activations