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

    Neuronpedia

    INDEX
    Explanations

    phrases related to currency, economy, or transactions

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions that indicate processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.74
    andowski
    -0.65
    Lv
    -0.56
     Canterbury
    -0.53
     Wrest
    -0.50
     Jed
    -0.49
    landish
    -0.49
    aii
    -0.48
    stellar
    -0.48
     presided
    -0.48
    POSITIVE LOGITS
    intensive
    0.64
    ãĥĺãĥ©
    0.61
    ocaust
    0.59
    atcher
    0.58
    aturation
    0.56
    ufact
    0.55
     itself
    0.54
     passively
    0.53
    afety
    0.50
    ãĤ´ãĥ³
    0.49
    Act Density 1.124%

    No Known Activations