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

    Neuronpedia

    INDEX
    Explanations

    references to the bringing together of different groups or elements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to unity and cooperation among groups or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earcher
    -0.66
    raid
    -0.65
    Administ
    -0.63
     ende
    -0.61
    adelphia
    -0.60
    &&
    -0.60
    tein
    -0.60
    govern
    -0.60
    ertation
    -0.59
    ording
    -0.59
    POSITIVE LOGITS
     closer
    1.18
     together
    1.08
     nearer
    1.08
     onto
    1.07
     back
    1.05
     into
    1.04
     crashing
    0.99
     forth
    0.98
     home
    0.88
    together
    0.85
    Act Density 0.139%

    No Known Activations