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

    Neuronpedia

    INDEX
    Explanations

    instances where a specific term 'added' is used in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "added" in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kat
    -0.61
    cheon
    -0.59
    FL
    -0.57
    wordpress
    -0.55
     VIDEOS
    -0.55
    kie
    -0.55
     Maker
    -0.54
    cdn
    -0.54
    gone
    -0.52
    cies
    -0.52
    POSITIVE LOGITS
    ictions
    1.01
     sarcast
    0.94
     omin
    0.92
    resso
    0.88
     emphatically
    0.82
     bluntly
    0.80
    endum
    0.79
     thereto
    0.78
     insult
    0.76
    igm
    0.76
    Act Density 0.038%

    No Known Activations