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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and terms indicating relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    人ãģ¯
    -0.16
    undler
    -0.15
    .scalablytyped
    -0.14
    IGHLIGHT
    -0.14
    ëĭĪëĭ¤
    -0.14
    groundColor
    -0.13
     hvordan
    -0.13
    IPH
    -0.13
    elim
    -0.13
    -UA
    -0.13
    POSITIVE LOGITS
     with
    0.16
    eto
    0.16
     inability
    0.15
    reso
    0.15
    ajÄħc
    0.15
    ÙĤاÙĦ
    0.14
    eton
    0.14
     unable
    0.14
     nurs
    0.14
     possibly
    0.14
    Act Density 0.175%

    No Known Activations