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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of items or contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enny
    -0.14
    znik
    -0.14
    its
    -0.14
    -ÑĤо
    -0.14
    /qu
    -0.14
    rend
    -0.14
    yster
    -0.14
     còn
    -0.14
    ero
    -0.14
    rap
    -0.14
    POSITIVE LOGITS
     elements
    0.17
    /embed
    0.17
    ational
    0.15
    erness
    0.15
    .mx
    0.15
     embedded
    0.14
    LESS
    0.14
    ãģ¡ãģ¯
    0.14
    ment
    0.14
     within
    0.14
    Act Density 0.024%

    No Known Activations