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

    Neuronpedia

    INDEX
    Explanations

    parameters and return values in key-value format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heim
    -0.66
    JIM
    -0.65
     pab
    -0.65
     WIND
    -0.63
    stor
    -0.63
    son
    -0.62
    ations
    -0.62
     μή
    -0.62
     JIM
    -0.62
    lis
    -0.61
    POSITIVE LOGITS
     =>
    1.55
    =>
    1.39
    )=>
    1.33
    (()=>
    1.19
    "=>
    1.17
     ()=>
    1.10
    ={()=>
    1.04
    =>"
    1.02
     ⇒
    1.00
     مرئيه
    0.98
    Act Density 0.022%

    No Known Activations