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

    Neuronpedia

    INDEX
    Explanations

    mentions of being part of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of being a part of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preceded
    -0.75
    ares
    -0.72
     Sections
    -0.71
    etimes
    -0.69
    atoon
    -0.68
    osponsors
    -0.67
    roads
    -0.65
    houses
    -0.65
    hips
    -0.65
    ences
    -0.65
    POSITIVE LOGITS
     equation
    1.40
     puzzle
    1.33
     reason
    1.14
     problem
    1.09
     solution
    1.08
     rationale
    0.96
     bargain
    0.96
     charm
    0.95
     story
    0.95
     explanation
    0.95
    Act Density 0.163%

    No Known Activations