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

    Neuronpedia

    INDEX
    Explanations

    text headers and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.54
    calciatore
    -0.53
    <eos>
    -0.50
    pera
    -0.48
    HasBeenSet
    -0.46
     An
    -0.46
     Y
    -0.45
     ,
    -0.42
     due
    -0.42
    னை
    -0.42
    POSITIVE LOGITS
     purpoſe
    1.03
     auffi
    1.00
     itſelf
    0.95
     uſed
    0.92
     myſelf
    0.91
     pleaſure
    0.89
     houſe
    0.88
     ſtate
    0.86
     himſelf
    0.86
     themſelves
    0.83
    Act Density 2.731%

    No Known Activations