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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote important additional information in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "crypto
    -0.17
     деле
    -0.14
    enu
    -0.14
    arget
    -0.14
    anim
    -0.13
    /Math
    -0.13
     esac
    -0.13
    IXEL
    -0.13
    باد
    -0.13
    uai
    -0.13
    POSITIVE LOGITS
    że
    0.22
    é¼
    0.14
    Äįil
    0.14
    amik
    0.14
    åĻ¨
    0.13
     Mand
    0.13
    LabelText
    0.13
    lick
    0.13
    olla
    0.13
     eman
    0.13
    Act Density 0.047%

    No Known Activations