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

    Neuronpedia

    INDEX
    Explanations

    words related to social relationships, particularly the term "peers."

    oai_token-act-pair · gpt-3.5-turbo

    references to social groups or relationships among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cer
    -0.88
    aton
    -0.71
    IFF
    -0.64
     Airl
    -0.63
    BN
    -0.63
    ston
    -0.61
    du
    -0.61
    upuncture
    -0.60
    lar
    -0.60
    uve
    -0.59
    POSITIVE LOGITS
    hip
    1.03
    ervative
    1.01
    folk
    0.99
    hips
    0.98
    heet
    0.94
    cript
    0.90
    ervatives
    0.89
    paces
    0.85
    mith
    0.85
    mates
    0.84
    Act Density 0.104%

    No Known Activations