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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols indicating positive and negative values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ريكية
    -0.43
     pouvoit
    -0.40
     bershka
    -0.39
    endphp
    -0.37
    enumii
    -0.36
     corrup
    -0.36
    Behavioral
    -0.36
    ház
    -0.36
     destru
    -0.36
    havior
    -0.35
    POSITIVE LOGITS
    ±
    0.73
     ± 
    0.66
     ±
    0.66
    pm
    0.65
    mailto
    0.62
    +#+#
    0.62
     operator
    0.60
    windowFixed
    0.59
     (±
    0.56
    aarrggbb
    0.56
    Act Density 0.304%

    No Known Activations