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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scientific research and methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.90
    ^(@)
    -0.89
    RTSC
    -0.89
     Reſ
    -0.88
    Personendaten
    -0.87
    sidemargin
    -0.87
     Houſe
    -0.86
     itſelf
    -0.86
     myſelf
    -0.86
    ſelves
    -0.85
    POSITIVE LOGITS
    .
    0.88
    ↵↵
    0.57
    ,
    0.48
    <eos>
    0.47
    ########.
    0.46
     [
    0.45
     CreateTagHelper
    0.43
     (
    0.42
    ...
    0.42
    ver
    0.41
    Act Density 0.875%

    No Known Activations