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

    Neuronpedia

    INDEX
    Explanations

    words related to military actions and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "had."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensing
    -0.62
    —-
    -0.60
    coin
    -0.58
    ocol
    -0.58
    hammer
    -0.58
     defense
    -0.57
    bie
    -0.56
     territ
    -0.56
    reciation
    -0.56
    lig
    -0.55
    POSITIVE LOGITS
     been
    1.22
     undergone
    1.13
     gone
    0.98
     begun
    0.97
    iths
    0.95
    raltar
    0.89
     become
    0.89
     gotten
    0.88
    ĸļ
    0.88
     taken
    0.87
    Act Density 0.155%

    No Known Activations