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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and certain phrases emphasizing connection and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zilla
    -0.16
    dge
    -0.15
    ambre
    -0.15
    orne
    -0.15
    olina
    -0.14
     Madden
    -0.14
    ÑĢава
    -0.14
    ilde
    -0.14
     Hawk
    -0.14
    oria
    -0.14
    POSITIVE LOGITS
     indeed
    0.18
    rog
    0.17
    238
    0.14
     mand
    0.14
    544
    0.14
    wu
    0.13
    rag
    0.13
    yny
    0.13
    ös
    0.13
    ¨ìĸ´
    0.13
    Act Density 0.161%

    No Known Activations