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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "that" followed by various verb forms or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤин
    -0.15
    inator
    -0.14
    Ñij
    -0.13
     tua
    -0.13
     Destiny
    -0.13
     although
    -0.13
    ilan
    -0.13
     tuo
    -0.12
     Hart
    -0.12
    Ñĥма
    -0.12
    POSITIVE LOGITS
    Brains
    0.15
    rien
    0.15
    -lfs
    0.14
    اج
    0.14
    opsy
    0.14
    .newaxis
    0.14
    uckland
    0.14
    .way
    0.14
    947
    0.14
    enga
    0.13
    Act Density 0.317%

    No Known Activations