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

    Neuronpedia

    INDEX
    Explanations

    instances of specific pronouns and temporal markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.89
    Autoritní
    -0.88
     CWE
    -0.81
    __':
    -0.81
     kaarangay
    -0.81
     Taktlose
    -0.74
    OGND
    -0.72
     propOrder
    -0.72
     resourceCulture
    -0.71
    +#+#
    -0.70
    POSITIVE LOGITS
     also
    0.85
     
    0.71
      
    0.69
     likewise
    0.68
    '
    0.65
     .
    0.64
     همچنین
    0.62
    同じく
    0.62
     in
    0.60
     others
    0.58
    Act Density 0.440%

    No Known Activations