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

    Neuronpedia

    INDEX
    Explanations

    references to open source projects and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.22
     Reſ
    -1.22
     purpoſe
    -1.20
     Diſ
    -1.19
     houſe
    -1.18
     himſelf
    -1.16
     Houſe
    -1.15
     Anſ
    -1.14
     ſtate
    -1.14
     Inſ
    -1.13
    POSITIVE LOGITS
    <eos>
    0.74
    ...
    0.68
     
    0.68
     A
    0.67
    ,
    0.64
     (
    0.64
    .
    0.61
    ↵
    0.60
    :
    0.60
     The
    0.60
    Act Density 2.007%

    No Known Activations