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

    Neuronpedia

    INDEX
    Explanations

    structured numerical data such as dates or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Instruction
    -0.15
    ERCHANT
    -0.14
    iversal
    -0.14
    ylon
    -0.14
    erin
    -0.14
    OURCES
    -0.14
    ache
    -0.14
    تÙĪر
    -0.14
    allis
    -0.14
    esson
    -0.13
    POSITIVE LOGITS
    æľĪ
    0.20
    /msg
    0.20
    ìĽĶ
    0.18
    -
    0.17
    íķĻ기
    0.17
    -DD
    0.16
     Cum
    0.16
    utow
    0.15
     æľĪ
    0.15
    ât
    0.14
    Act Density 0.022%

    No Known Activations