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

    Neuronpedia

    INDEX
    Explanations

    words related to forming a basis or foundation for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terminology related to foundational principles or bases of arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overheard
    -0.76
     exchanged
    -0.65
     snapped
    -0.65
     disrupted
    -0.62
     booked
    -0.60
     lined
    -0.60
    icken
    -0.60
     showcased
    -0.60
     interfered
    -0.59
     collide
    -0.59
    POSITIVE LOGITS
     blame
    0.96
    vre
    0.83
     emphasis
    0.81
    sole
    0.79
     squarely
    0.78
     solely
    0.76
     scorn
    0.72
    haar
    0.70
     fortunes
    0.69
     chiefly
    0.69
    Act Density 0.153%

    No Known Activations