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

    Neuronpedia

    INDEX
    Explanations

    various forms of verbs indicating initiation or action progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coliseum
    -0.63
     cowardice
    -0.63
     Frisch
    -0.60
    Fris
    -0.57
    EndContext
    -0.55
     oath
    -0.53
     Söder
    -0.52
     acacia
    -0.51
    Surviving
    -0.51
     pectin
    -0.50
    POSITIVE LOGITS
     began
    1.06
     begins
    1.00
     begin
    0.97
    began
    0.93
     begun
    0.93
     started
    0.88
     empiezan
    0.88
     starts
    0.86
     Begin
    0.82
     Began
    0.82
    Act Density 0.153%

    No Known Activations