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

    Neuronpedia

    INDEX
    Explanations

    instances of possessive ownership or affiliation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nah
    -0.62
    ply
    -0.60
    ener
    -0.60
    abre
    -0.59
    asia
    -0.59
    uce
    -0.59
    ean
    -0.59
    edu
    -0.58
     fuzz
    -0.57
    dayName
    -0.57
    POSITIVE LOGITS
    ighth
    0.64
    idges
    0.63
     liberty
    0.62
     whom
    0.61
     civilization
    0.60
     Mankind
    0.58
    assisted
    0.58
    ãĥĩ
    0.58
    hire
    0.57
    ãĥīãĥ©
    0.56
    Act Density 0.163%

    No Known Activations