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

    Neuronpedia

    INDEX
    Explanations

    blocks of template or data syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.13
     kasarigan
    -1.09
     autorytatywna
    -1.00
    Datuak
    -0.99
    <unused43>
    -0.97
    <pad>
    -0.96
    <unused41>
    -0.96
    <unused23>
    -0.95
    <unused17>
    -0.95
    <unused3>
    -0.94
    POSITIVE LOGITS
    {{
    0.81
     United
    0.78
     
    0.73
     {{
    0.72
     the
    0.70
     within
    0.69
     inter
    0.68
     "
    0.64
    '
    0.63
     (
    0.63
    Act Density 0.310%

    No Known Activations