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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    special characters or empty strings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patriarch
    -0.69
     Nieto
    -0.68
     Mellon
    -0.64
     Miko
    -0.64
     machine
    -0.63
     Synd
    -0.63
     Hole
    -0.62
     fringe
    -0.62
    xus
    -0.62
     Leopard
    -0.61
    POSITIVE LOGITS
    rozen
    1.39
    requently
    1.37
    ortun
    1.36
    ortunate
    1.33
    ocusing
    1.32
    avour
    1.31
    amiliar
    1.29
    ocused
    1.28
    luent
    1.26
    requency
    1.26
    Act Density 0.049%

    No Known Activations