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

    Neuronpedia

    INDEX
    Explanations

    combinations of words related to searching, examining, or analyzing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to combing or combining elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SAY
    -0.64
    mos
    -0.63
     Royals
    -0.63
     silence
    -0.62
     Defenders
    -0.62
     OWN
    -0.60
    Demand
    -0.60
    VICE
    -0.59
     Wilde
    -0.58
     Confederacy
    -0.58
    POSITIVE LOGITS
    inators
    1.29
    inator
    1.27
    inatory
    1.20
    inational
    1.18
    ative
    1.07
    itsch
    1.00
    atform
    1.00
    ats
    0.96
    inations
    0.93
    asso
    0.91
    Act Density 0.024%

    No Known Activations