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

    Neuronpedia

    INDEX
    Explanations

    commonalities or shared characteristics between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate shared characteristics or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icer
    -0.70
    hement
    -0.66
    renheit
    -0.65
     Accountability
    -0.65
    veland
    -0.65
    ctors
    -0.65
    ighth
    -0.64
    gur
    -0.63
    zona
    -0.62
    bable
    -0.61
    POSITIVE LOGITS
    alities
    0.97
     similarities
    0.83
     resemb
    0.83
     resemblance
    0.78
    worldly
    0.70
     distinguishing
    0.70
     twins
    0.68
     resembling
    0.67
     resemble
    0.67
    DragonMagazine
    0.66
    Act Density 0.065%

    No Known Activations