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

    Neuronpedia

    INDEX
    Explanations

    blocks of text that indicate the beginning of a new section or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ian
    -0.66
    رائ
    -0.65
     Maria
    -0.63
    ––––
    -0.59
    hy
    -0.59
     Fra
    -0.59
    Maria
    -0.58
     Р
    -0.57
    дей
    -0.57
    μέ
    -0.57
    POSITIVE LOGITS
     Connect
    1.06
    Connect
    0.98
    connect
    0.96
     CONNECT
    0.93
    Locate
    0.92
    hdessä
    0.89
     Arrive
    0.88
    jectures
    0.88
     myſelf
    0.88
     Monfieur
    0.88
    Act Density 0.012%

    No Known Activations