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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" used as an infinitive marker or in phrases indicating intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    actions beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.48
    delwed
    -0.41
     AssemblyCompany
    -0.41
     loung
    -0.40
     identically
    -0.40
     kaynağından
    -0.38
    GEBURTS
    -0.37
    Portály
    -0.37
     butterknife
    -0.36
     jamás
    -0.36
    POSITIVE LOGITS
     begins
    0.63
    Slowly
    0.63
     began
    0.63
     mulai
    0.62
     slowly
    0.62
     zač
    0.61
     begun
    0.60
     begin
    0.60
     начинает
    0.59
     empiezan
    0.58
    Act Density 0.011%

    No Known Activations