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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the start of a process or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "began."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etry
    -0.80
    acho
    -0.72
    rats
    -0.69
    stood
    -0.67
    houses
    -0.67
    outer
    -0.65
    Zone
    -0.64
    ado
    -0.64
    iliary
    -0.63
    aths
    -0.63
    POSITIVE LOGITS
     anew
    1.07
    EStream
    0.75
    NetMessage
    0.74
    ŃĶ
    0.73
    ITIES
    0.70
     PRESS
    0.70
     withd
    0.69
    OPLE
    0.69
    20439
    0.68
    Ò
    0.68
    Act Density 0.039%

    No Known Activations