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

    Neuronpedia

    INDEX
    Explanations

    verbs or adjectives related to distinguishing or differentiating between objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to differentiation and distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WR
    -0.70
     Omni
    -0.70
     Fulton
    -0.67
    MN
    -0.64
    aptic
    -0.64
    odder
    -0.63
    Assembly
    -0.63
     Apostles
    -0.63
    rollers
    -0.63
     havoc
    -0.62
    POSITIVE LOGITS
     between
    1.05
    ively
    1.03
    iates
    0.95
     distinctions
    0.95
    iveness
    0.94
     distinguish
    0.92
     sexes
    0.90
     Between
    0.87
     distinguishing
    0.85
    between
    0.84
    Act Density 0.043%

    No Known Activations