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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating possession or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poser
    -0.17
    )prepare
    -0.17
    Ïģκ
    -0.16
    thalm
    -0.15
    CLAIM
    -0.15
    ehir
    -0.14
    ož
    -0.14
    orado
    -0.14
     Bei
    -0.14
    andon
    -0.14
    POSITIVE LOGITS
    acy
    0.15
    itudes
    0.14
     certain
    0.14
    reamble
    0.14
    uppe
    0.14
    (credentials
    0.14
    les
    0.13
    heits
    0.13
    .ribbon
    0.13
    ÅĻenÃŃ
    0.13
    Act Density 0.248%

    No Known Activations