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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistical distributions and ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.42
    seteq
    -0.41
    <bos>
    -0.38
    maketitle
    -0.35
     bomb
    -0.35
     Intr
    -0.34
    FXML
    -0.34
    فاده
    -0.34
    cciale
    -0.34
    ombic
    -0.33
    POSITIVE LOGITS
     poffible
    0.57
     gethan
    0.56
     miniaturka
    0.53
    MessageTagHelper
    0.52
     quæ
    0.51
     stderr
    0.50
     nothwendig
    0.49
     $_(
    0.48
     ciąży
    0.47
     čierna
    0.45
    Act Density 0.020%

    No Known Activations