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

    Neuronpedia

    INDEX
    Explanations

    expressions of moral justification and legality concerning actions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ButtonItem
    -0.15
    lsa
    -0.14
    èĬĿ
    -0.14
     me
    -0.14
    alties
    -0.13
     Shea
    -0.13
    kes
    -0.13
    utin
    -0.13
     promise
    -0.13
    ires
    -0.13
    POSITIVE LOGITS
     buc
    0.16
    koa
    0.15
     adulte
    0.15
    .createComponent
    0.14
    aret
    0.14
    zag
    0.14
    /legal
    0.14
    asca
    0.14
    azor
    0.14
    .writeValue
    0.14
    Act Density 0.268%

    No Known Activations