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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of separating or dismantling

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "de-" indicating a process of removal or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wage
    -0.64
    imum
    -0.62
     Teacher
    -0.58
     AAP
    -0.57
    SHIP
    -0.57
     wage
    -0.56
     cartridges
    -0.55
     Sheet
    -0.55
     sockets
    -0.55
    ULAR
    -0.53
    POSITIVE LOGITS
     facto
    1.31
    pleting
    1.18
    arest
    1.16
    arth
    1.14
     Blasio
    1.14
    cember
    1.13
    utsche
    1.13
    activated
    1.12
    cept
    1.10
    vious
    1.10
    Act Density 0.024%

    No Known Activations