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

    Neuronpedia

    INDEX
    Explanations

    phrases advocating for action and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*@
    -0.18
    ines
    -0.14
    pecies
    -0.14
    ail
    -0.14
    HEMA
    -0.14
    yne
    -0.14
    Disc
    -0.13
    ancy
    -0.13
    ito
    -0.13
    etry
    -0.13
    POSITIVE LOGITS
     secure
    0.15
    mw
    0.15
    ipl
    0.14
    iem
    0.14
    izik
    0.14
    osy
    0.14
    raphics
    0.14
     ensuring
    0.14
    cec
    0.14
    opak
    0.14
    Act Density 0.086%

    No Known Activations