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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating arrival or approach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Szk
    -0.54
     Bacteriol
    -0.54
    printStats
    -0.54
     judiciaire
    -0.52
     PRACT
    -0.51
    stasi
    -0.49
    ByUserId
    -0.48
    eraard
    -0.48
    ientras
    -0.48
     préféré
    -0.48
    POSITIVE LOGITS
     come
    1.22
     comes
    1.14
     came
    1.14
    Comes
    1.11
     Comes
    1.10
    come
    1.07
     Come
    1.05
    came
    1.05
    comes
    1.04
    Come
    1.04
    Act Density 0.114%

    No Known Activations