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

    Neuronpedia

    INDEX
    Explanations

    terms related to intelligence and intellectual themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.69
    :+:
    -0.61
     nahilalakip
    -0.58
    therford
    -0.58
    mények
    -0.56
     Walkover
    -0.55
    vieja
    -0.55
    şört
    -0.53
    רושלים
    -0.53
     gainera
    -0.53
    POSITIVE LOGITS
     intelligen
    0.89
     Intelligen
    0.85
     intellig
    0.85
     Intelli
    0.84
    Intelligent
    0.84
     Intelligent
    0.82
     inteligen
    0.82
     intellect
    0.81
     INTELL
    0.81
     intelligence
    0.80
    Act Density 0.128%

    No Known Activations