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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conversation and dialogue

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" as a conjunction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.91
    owered
    -0.89
    OWN
    -0.74
    ãĤ´ãĥ³
    -0.74
    escription
    -0.69
     pione
    -0.69
    zan
    -0.69
    ongyang
    -0.68
    Initialized
    -0.68
    cko
    -0.67
    POSITIVE LOGITS
     plenty
    1.17
     lots
    1.16
     secondly
    1.05
     luckily
    1.03
     there
    1.03
     maybe
    1.00
     we
    0.99
     moreover
    0.97
     hopefully
    0.96
     tons
    0.95
    Act Density 0.295%

    No Known Activations