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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deception or fraud

    oai_token-act-pair · gpt-3.5-turbo

    words related to states of being or emotional conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     frag
    -0.69
     Sinai
    -0.64
     Du
    -0.63
     refin
    -0.63
     persu
    -0.63
    ship
    -0.60
     behind
    -0.59
     upgrading
    -0.59
     than
    -0.58
     stamp
    -0.58
    POSITIVE LOGITS
    oked
    4.43
    okes
    1.78
    oke
    1.60
    oking
    1.27
    okers
    1.21
    oker
    1.18
    oks
    1.14
    ocative
    1.11
    ocated
    1.05
    oled
    1.05
    Act Density 0.007%

    No Known Activations