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

    Neuronpedia

    INDEX
    Explanations

    the usage of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.79
     itſelf
    -0.69
     houſe
    -0.69
     Lightboxes
    -0.64
     Himo
    -0.61
     Portail
    -0.60
     Shakspeare
    -0.60
     Pergamon
    -0.59
    ſelves
    -0.59
     ariel
    -0.58
    POSITIVE LOGITS
     there
    1.32
     they
    1.25
     it
    1.17
     we
    1.16
    there
    0.92
     he
    0.87
    毕竟
    0.85
     she
    0.81
     because
    0.79
    畢竟
    0.78
    Act Density 0.224%

    No Known Activations